Bernat Cuni Bernat Cuni

Deep Textures

Using Machine Learning to create unexpected materials with textures and normal data.

Using Machine Learning to create unexpected materials with textures and normal data.

A [remote] artist residency at Runway, a company that develop tools to make machine learning more accessible for creators.

Results:

Browse / Download 150 textures [google drive]

  • mouse wheel/pinch= zoom
  • click/tap + drag / arrow keys = rotate
  • *doesn't seem to work with Safari desktop

    • Here a curated selection of specially beautiful textures and normal maps

    Play / Models released at Runway

    Motivation:

    Having extensively used CAD & 3D software packages as part of my product designer practice, I personally find the task of creating new materials tedious and expectable, without a surprise factor. On the other and, with my playing with GANs and image-based ML tools has a discovery factor that keeps me engaged with rewards of nice findings while exploring the unknown.

    So, how could we create new 3D materials using GANs?

    Proof of concept:

    In order to test the look & feel of ML generated 3D materials, I ran a collection of 1000 Portuguese Azulejo Tiles images through StyleGAN to generate visually similar tiles. The results are surprisingly nice, so this seems to be a good direction.

    Next step was to add depth to those generated images.

    3D packages can read BW data and render it as height transformation (bump map), if this is done with the same image used as texture, results are ok but not accurate, as different colours with similar saturation will show with the same height :(.

    So, I had to find translation tool to identify/segment which part of the tiles are embossed or extruded to add some height detail.

    To add depth to those tiles, I ran some of them through DenseDepth model, and I got some interpertations of depth as grayscale images, not accurate probably because the model is trained with spatial scenes (Indoor and outdoor), but the results were beautiful and interesting.

    DeepTiles02.png
    800px-Normal_map_example_with_scene_and_result.png

    Approach

    The initial idea is to source a dataset composed of texture images (diffuse) and their corresponding normal map (a technique used for faking the lighting of bumps and dents. Normal maps are commonly stored as regular RGB images where the RGB components correspond to the X, Y, and Z coordinates, respectively, of the surface normal).

    And then ran those images through StyleGAN.

    It would ideal be to have two StyleGAN's to talk to each other while learning, so they'd know which normal-map relates to which texture... But doing that is beyond my current knowledge.

    A workaround could be to stitch/merge both Diffuse + Normal textures into a single image, and ran it through the StyleGAN, with the hope that it would understand that there are two different and corresponding sides of each image, and thus, generate images with both sides... for later splitting them in order to get the generated diffuse and the corresponding generated normal.

    But first, I need to see if the model is good at generating diffuse texture images from a highly diverse dataset containign bricks, fur, wood, foam... (probably yes, as it did with the Azulejo, but needs to be tested).

    Diffuse Texture generation

    The Dataset chosen is Describable Textures Dataset (DTD) a texture database, consisting of 5640 images, organized according to a list of 47 terms (categories) inspired from human perception. There are 120 images for each category.

    The results are surprisingly consistent and rich, considering that some categories have confusing textures that are not “full-frame” but appear in objects or in context. i.e: “freckles”, “hair” or “foam”.

    Describable Textures Dataset (DTD)

    Describable Textures Dataset (DTD)

    Normal Map generation

    Finding a good dataset of normal-maps has been challenging, since there's an abundance of textures for sale but a scarcity of freely accessible ones. Initially I attempted to scrape some sites containing free textures, but it required too much effort to collect few hundred textures.

    A first test was done with the dataset provided by the Single-Image SVBRDF Capture with a Rendering-Aware Deep Network project.
    From this [85GB zipped] dataset I cropped and isolated a subset of 2700 normal map images to feed the StyleGAN training.

    Dataset: Normal Maps

    StyleGAN was able to understand what makes a normal map, and it generates consistent images, with the colors correctly placed.
    I then ran the generated normal maps through blender to see how they drive light within a 3D environment.

    Diffuse + Normal Map single image StyleGAN training.

    Now I knew that StyleGAN was capable of generating nice textures and nice normal maps independently, but I needed the normal maps to correlate to the diffuse information. Since I wasn’t able to make two stylegans talk to each other while training, I opted for composing a dataset containing the diffuse and the normal map within a single image.

    This time I choose cc0textures which has a good repository of PBR textures and provides a csv information that can be used to download the desired files via wget.

    Dataset: 790 images

    Dataset: 790 images

    The generated images are beautiful and they work as expected.

    StyleGAN is able to understand that both sides of the images are very different and respects that when generating content.

    it works! The normal maps look nice and correspond to the diffuse features.

    What if?…

    The diffuse images generated with the image-pairs are a bit weak and uninteresting, because the source dataset isn’t as bright and variate as the DTD. But unfortunately the DTD doesn’t have normal maps associated. :(

    I want a rich diffuse texture and a corresponding normal map… 🤔

    Normal map generation from source diffuse texture

    I had to find a wat to turn any given image into a somehow working normal map. To do this, I tested Pix2Pix (Image-to-Image Translation with Conditional Adversarial Nets) with the image pairs composed for the previous experiment.

    I trained it locally with 790 images, and after 32h of training I had some nice results:

    Pix2Pix generates consistent normal maps of any given texture.

    Chaining models

    Workflow idea: 

    Diffuse from StyleGAN -> input to Pix2Pix -> generate the corresponding normal map

    First I had to brig the Pix2Pix trained model to Runway. [following these steps].

    Then I used StyleGAN’s output as Pix2Pix Input. 👍

    With the help of Brannon Dorsey and following this fantastic tutorial from Daniel Shiffman, we were able to run a P5js sketch to generate randomGaussian vectors for StyleGAN, and use that output to feed Pix2Pix and generate the normal-maps.

    Final tests / model selection

    From all the tests, the learnings are the following:

    • Stylegan for textures works good - [SELECTED] - dataset = 5400 images

    • StyleGAN for normal maps works good, but there’s no way to link the generated maps to diffuse textures - [DISCARDED]

    • StyleGAN trained with a 2-in-one dataset produces nice and consistent results - but the datasets used did not produce varied and rich textures. [DISCARDED]

    • Pix2Pix to generate normal maps from a given diffuse texture works good. [SELECTED] - dataset = 790 image pairs

    • Pix2Pix trained with 10000 images produced weak results. [DISCARDED]

    The final approach is: StyleGan trained with textures from the DTD dataset (5400 images) -> Pix2Pix trained with a small (790) dataset of Diffuse-Normal pairs from cc0Textures

    Visualization & Interaction

    I really like how runway visualises the latent space using a 2D grid to explore a multi-dimensional space of possibilities. (in resonance with some of the ideas in this article: Rethinking Design Tools in the Age of Machine Learning ).

    It would be great to build a similar approach to explore the generated textures within a 3D environment.

    To visualise textured 3D models on the web, I explored Three.js and other tools.

    babylonjs seems the best suited for this project.:

    A quick test with the textures generated from StyleGAN looks nice enough.

    Trying to add the grid effect found in runway makes the thing a bit slower but interesting. The challenge is how to change the textures on-the´fly with the ones generated by StyleGAN/Pix2Pix…

    After some tests and experimentations I managed to load video textures, and display them within a realtime web interface. 👍

    • mouse wheel/pinch= zoom

    • click/tap + drag / arrow keys = rotate

    • *doesn't seem to work with Safari desktop

    Learnings & Release

    The StyleGAN behaved as expeced: producing more interesting results when given a more rich and varied dataset.
    Pix2Pix model has proven strong enough, but results could be better. For next iterations of this idea I should explore other models. like MUNIT or even some StyleTransfer approach.

    Both checkpoints have been released and are free to use at Runway. StyleGAN-Textures + Diffuse-2-Normal

    You can also download the model files here for your local use.

    Thanks & next

    This project has been done in about two weeks, within the Something-in-Residence program at RunwayML. Thanks.

    I’ve learned a lot during this project and I’m ready to build more tools and experiments blending Design/AI/3D/Crafts and help others play with ML.

    For questions, comments and collaborations, please let me know -> contact here or via twitter.

    Background & Glossary

    Some impressive work has been previously done in that area:

    Texture Synthesis Using Convolutional Neural Networks

    Some prints:

    Featured
    _deepTextures_002_p_mockup_Transparent_Transparent_16x20.jpg
    Deep Textures 001
    €25.00
    _deepTextures_003_p_mockup_Transparent_Transparent_16x20.png
    Deep Textures 002
    €25.00
    _deepAzulejo_000_p_mockup_Transparent_Transparent_16x20.png
    Deep Azulejo 000
    €25.00
    Read More
    Bernat Cuni Bernat Cuni

    confusing coleopterists / 🤔🐞

    breeding bugs in the latent space

    breeding bugs in the latent space

    A beetle generator made by machine-learning thousands of #PublicDomain illustrations.

    Inspired by the stream of new Machine Learning tools being developed and made accessible and how they can be used by the creative industries, I was curious to run some visual experiments with a nice source material: zoological illustrations.

    Previously I ran some test with DeepDream and StyleTransfer, but after discovering the material published at Machine Learning for Artists / @ml4a_ , I decided to experiment with the Generative Adversarial Network (GAN) approach.

    Creating a Dataset

    Through the Biodiversity Heritage Library, I discovered the book: Biologia Centrali-Americana :zoology, botany and archaeology, hosted at archive.org, containing fantastic #PublicDomain illustrations of beetles.

    Through a combination of OpenCV and ImageMagick, I managed to extract each individual illustration and generate nicely centered square images.

    Training a GAN

    Following the Lecture 6: Generative models  [10/23/2018] The Neural Aesthetic @ ITP-NYU, Fall 2018 - [ Lecture 6: Generative models  [10/23/2018] -> Training DCGAN-tensorflow (2:27:07) ] I managed to run DCGAN with my dataset and paying with different epochs and settings I got this sets of quasi-beetles.

    Nice, but ugly as cockroaches

    it was time to abandone DCGAN and try StyleGAN

    Expected training times for the default configuration using Tesla V100 GPUs

    Expected training times for the default configuration using Tesla V100 GPUs

    Training StyleGAN

    I set up a machine at PaperSpace with 1 GPU (According to NVIDIA’s repository, running StyleGan on 256px images takes over 14 days with 1 Tesla GPU) 😅

    I trained it with 128px images and ran it for > 3 days, costing > €125.

    Results were nice! but tiny.

    Generating outputs

    Since PaperSpace is expensive (useful but expensive), I moved to Google Colab [which has 12 hours of K80 GPU per run for free] to generate the outputs using this StyleGAN notebook.

    Results were interesting and mesmerising, but 128px beetles are too small, so the project rested inside the fat IdeasForLater folder in my laptop for some months.

    ConfusingColeopterists_packed_post.png

    In parallel, I've been playing with Runway, a fantastic tool for creative experimentation with machine learning. And in late November 2019 the training feature was ready for beta-testing.

    Training in HD

    I loaded the beetle dataset and trained it at full 1024px, [on top of the FlickrHD model] and after 3000 steps the results were very nice.

    From Runway, I saved the 1024px model and moved it to Google Colab to generated some HD outputs.

    In December 2019 StyleGAN 2 was released, and I was able to load the StyleGAN (1) model into this StyleGAN2 notebook and run some experiments like "Projecting images onto the generatable manifold", which finds the closest generatable image based on any input image, and explored the Beetles vs Beatles:

    model released

    make your own fake beetles with RunwayML -> start

    confusing coleopterists - postcards - 01002.png

    1/1 edition postcards

    BUY HERE

    AI Bugs a crypto-collectibles

    Since there is an infinite number of potential beetles that the GAN can generate, I tested adding a coat of artificial scarcity and post some outputs at Makersplace as digital collectibles on the blockchain... 🙄🤦‍♂️

    AI bugs as a prints

    I then extracted the frames from the interpolation videos and created nicely organised grids that look fantastic as framed prints and posters, and made them available via Society6.

    Framed prints available in six sizes, in a white or black frame color.

    • Every product is made just for you

    • Natural white, matte, 100% cotton rag, acid and lignin-free archival paper

    • Gesso coating for rich color and smooth finish

    • Premium shatterproof acrylic cover

    • Frame dimensions: 1.06" (W) x 0.625" (D)

    • Wire or sawtooth hanger included depending on size (does not include hanging hardware)

    il_794xN.2182813013_swxd.jpg

    random

    mini print

    each print is unique [framed]

    BUY HERE

    As custom prints (via etsy)

    glossary & links

    Machine learning (ML) is the scientific study of algorithms and statistical models that computer systems use to perform a specific task without using explicit instructions, relying on patterns and inference instead. It is seen as a subset of artificial intelligence. Machine learning algorithms build a mathematical model based on sample data, known as "training data", in order to make predictions or decisions without being explicitly programmed to perform the task.[1][2]:2 Machine learning algorithms are used in a wide variety of applications, such as email filtering and computer vision, where it is difficult or infeasible to develop a conventional algorithm for effectively performing the task.

    Machine learning is closely related to computational statistics, which focuses on making predictions using computers. The study of mathematical optimization delivers methods, theory and application domains to the field of machine learning. Data mining is a field of study within machine learning, and focuses on exploratory data analysis through unsupervised learning.[3][4] In its application across business problems, machine learning is also referred to as predictive analytics.

    The name machine learning was coined in 1959 by Arthur Samuel.[5] Tom M. Mitchell provided a widely quoted, more formal definition of the algorithms studied in the machine learning field: "A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E."[6] This definition of the tasks in which machine learning is concerned offers a fundamentally operational definition rather than defining the field in cognitive terms. This follows Alan Turing's proposal in his paper "Computing Machinery and Intelligence", in which the question "Can machines think?" is replaced with the question "Can machines do what we (as thinking entities) can do?".[7] In Turing's proposal the various characteristics that could be possessed by a thinking machine and the various implications in constructing one are exposed.

    Machine learning ( ML) is the scientific study of algorithms and statistical models that computer systems use to perform a specific task without using explicit instructions, relying on patterns and inference instead. It is seen as a subset of artificial intelligence.

    A generative adversarial network (GAN) is a class of machine learning systems invented by Ian Goodfellow and his colleagues in 2014.[1] Two neural networks contest with each other in a game (in the sense of game theory, often but not always in the form of a zero-sum game). Given a training set, this technique learns to generate new data with the same statistics as the training set. For example, a GAN trained on photographs can generate new photographs that look at least superficially authentic to human observers, having many realistic characteristics. Though originally proposed as a form of generative model for unsupervised learning, GANs have also proven useful for semi-supervised learning,[2] fully supervised learning,[3] and reinforcement learning.[4] In a 2016 seminar, Yann LeCun described GANs as "the coolest idea in machine learning in the last twenty years".[5]

    The generative network generates candidates while the discriminative network evaluates them.[1] The contest operates in terms of data distributions. Typically, the generative network learns to map from a latent space to a data distribution of interest, while the discriminative network distinguishes candidates produced by the generator from the true data distribution. The generative network's training objective is to increase the error rate of the discriminative network (i.e., "fool" the discriminator network by producing novel candidates that the discriminator thinks are not synthesized (are part of the true data distribution)).[1][6]

    A known dataset serves as the initial training data for the discriminator. Training it involves presenting it with samples from the training dataset, until it achieves acceptable accuracy. The generator trains based on whether it succeeds in fooling the discriminator. Typically the generator is seeded with randomized input that is sampled from a predefined latent space (e.g. a multivariate normal distribution). Thereafter, candidates synthesized by the generator are evaluated by the discriminator. Backpropagation is applied in both networks so that the generator produces better images, while the discriminator becomes more skilled at flagging synthetic images.[7] The generator is typically a deconvolutional neural network, and the discriminator is a convolutional neural network.

    A generative adversarial network ( GAN) is a class of machine learning systems invented by Ian Goodfellow and his colleagues in 2014. Two neural networks contest with each other in a game (in the sense of game theory, often but not always in the form of a zero-sum game).

    StyleGAN is a novel generative adversarial network (GAN) introduced by Nvidia researchers in December 2018,[1] and open sourced in February 2019.[2][3]

    StyleGAN depends on Nvidia's CUDA software, GPUs and on TensorFlow.[4]

    The website This Person Does Not Exist showcases fully automated human image synthesis by endlessly generating images that look like facial portraits of human faces.[5] The website was published in February 2019 by Phillip Wang. The technology has drawn comparison with deep fakes[6] and the tells of poker, and its potential usage for sinister purposes has been bruited.[7]

    The website This Person Does Not Exist showcases fully automated human image synthesis by endlessly generating images that look like facial portraits of human faces. The website was published in February 2019 by Phillip Wang. The technology has drawn comparison with deep fakes and the tells of poker, and its potential usage for sinister purposes has been bruited.

    DeepDream is a computer vision program created by Google engineer Alexander Mordvintsev which uses a convolutional neural network to find and enhance patterns in images via algorithmic pareidolia, thus creating a dream-like hallucinogenic appearance in the deliberately over-processed images.[1][2][3]

    Google's program popularized the term (deep) "dreaming" to refer to the generation of images that produce desired activations in a trained deep network, and the term now refers to a collection of related approaches.

    The DeepDream software originated in a deep convolutional network codenamed "Inception" after the film of the same name,[1][2][3] was developed for the ImageNet Large-Scale Visual Recognition Challenge (ILSVRC) in 2014[3] and released in July 2015.

    DeepDream is a computer vision program created by Google engineer Alexander Mordvintsev which uses a convolutional neural network to find and enhance patterns in images via algorithmic pareidolia, thus creating a dream-like hallucinogenic appearance in the deliberately over-processed images.

    Read More
    Bernat Cuni Bernat Cuni

    HEADFOAM

    Design and test of shock-absorbing structures produced by AM to be applied to helmets used as PPE (Personal Protective Equipment) in sports as climbing, biking, skating, etc.

    Shock Absorbing Structures For Sports Helmet

    Head Protective Equipment Fabricated With Additive Manufacturing

    Project: Design and test of shock-absorbing structures produced by AM to be applied to helmets used as PPE (Personal Protective Equipment) in sports as climbing, biking, skating, etc.

    Innovation: Use of an impact-absorbing structure designed specifically for AM production.

    Challenge: We believe that an inner structure of a safety helmet designed with a shock-absorbing lattice structure and produced by AM would make a better helmet.

    Application: The solution PPE helmet can be used in outdoors sports as climbing or biking or skating..

    Activities:

    Design study on several techniques to generate lattice structures.

    01 lattice design.jpg

    Fabrication of test probes produced in MJF PA11 and SLS TPU

    Dynamic Impact Tests

    Test consisted in dropping 5 kg round metal object onto the test subject from a height of 1m. Test was run at the User Partner lab, equipped with testing machinery, using the 1011e 1012_MAU 1002_2W ALU_SF equipment by CKL engineering (figure 3 left). Machine measures the total impact force which is absorbed by the sample, measured in Newtons.

    Test results evaluation

    Helmet inner part designed with shock absorbing lattice

    prototypes & tests

    LaaS / Lattice as a Service

    H2020_logo_500px.jpg

    This project has received funding from the European Union’s H2020 Framework Programme for research, technological development and demonstration under grant agreement no 768775.

    Project supported by AMable and I4MS, done In collaboration with: ProductosClimax S.A.

    AMable [AdditiveManufacturABLE ] provides support to SMEs and mid-caps for their individual uptake of additive manufacturing. Across all technologies from plastics through polymers to metals, AMable offers services that target challenges for newcomers, enthusiasts and experts alike.

    I4MS -> The EU initiative to digitalise the manufacturing industry

    Read More
    Bernat Cuni Bernat Cuni

    SheDavid

    3DScan Mashup / Venus de Milo + Michelangelo’s David

    3DScan Mashup

    Venus de Milo + Michelangelo’s David

    Sculpture / 3D Printed in StainlessSteel

    Sculpture / 3D Printed in StainlessSteel


    Read More
    Bernat Cuni Bernat Cuni

    mootioon.com

    Curated stream of inspiring  3D & MotionGraphics.

    mootioon -> 3D / MotionGraphics / Render / Loop / C4D -> stream

    An experiment to create a custom TV channel with an endless stream of inspiring motion graphics, 3D, vfx and CGI clips.

    Inspired by the weird and mesmerising short-clips that inundated MTv during the 90’s, I always wanted a TV channel full of that, so I built one.

    • A script continuously finds clips from several sources

    • OBS to streams a folder containing the clips, randomly

    • Restream splits the feed to Twitch / Youtube

    • The site links to most of the identified artists.

    • The service built for fun, and it doesn’t make money.

    -> youtube / twitch / instagram

    Read More
    Bernat Cuni Bernat Cuni

    Agencies

    Use 3D Printing in your next project: designing and preparing 3D models for 3D printing.

    3D Print for Creative Agencies & Studios

    Use 3D Printing in your next project, we help you by designing and preparing 3D models ready for 3D printing.

    🛠 Problem: You want to use 3D Printing but don’t know how to start.

    ⚡️ Solution: We will assess if the project is doable or no and help you to make it real.

    ✏️ About us: We have extensive experience with 3D Printing in multiple projects.

    🤔 You are an agency and got a fantastic project, and are thinking to use 3D printing: either to make a trophy for an event, create props for a photoshoot, or produce a short batch of items for a campaign.

    Great idea! Probably everyone in the team has heard about 3D Printing, but most likely no one knows how to execute it :(

    so, you might have some of the following questions:

    • - which materials shall we use?

    • - can we make something in colour?

    • - can we make something with metal?

    • - can we make something with ceramics?

    • - can we make something with flexible material?

    • - where to 3D Print?

    • - how expensive can it be?

    You might have some talented designers on your team, and hopefully some master 3D modelling applications.

    Sounds perfect, you should be ready to roll, but turns out that none of them have extensive experience with 3D Printing :( thus, there's a high probability that what they can design can't be 3D Printed due to constrains on the 3D Printing process.

    So, your designers might have some of the following questions:

    • - how to create something to be 3D Printed?

    • - can I print multiple parts in one go?

    • - can my design have interlocking parts?

    • - what is the appropriate wall thickness?

    • - can the model be solid?

    • - shall the model be hollow?

    • - what is a "watertight" 3D model?

    • - how to remove manifold edges?

    👍 We have extensive experience with 3D Printing in multiple materials, we have produced unique parts for clients, master pieces for molds, small batch series for product launches, personalised trophies, jewerly and ceramic products.

    • We will help you to assess if the project is doable or not. - for free -

    • Choose the appropriate material.

    • Design and 3D model for an optimal 3D printing.

    • Find a 3D Printing provider near you.

    • And help you produce the parts.

    How it works:

    You will work with a skilled product designer to create a design for your project.
    We can start from scratch or evolve a product and re-design it for 3D Printing.

    1 / Consultation / free

    • Assess if 3D printing is the best tech for your project.

    • -> Chat with us, or schedule a quick meeting to discuss your thoughts.

    2 / Project Brief

    • Understand project goals.

    • Design inspiration.

    • Define materials.

    • Estimate production costs.

    3 / Design phase

    • An expert 3D modeller will envision and prepare your design.

    • Iterative sessions where you will provide feedback in order to match expectations before production.

    • We will deliver a 3D file along with a final quotation of the production costs.

    4 / Production & Shipping

    • 3D Printed parts are made and delivered.

    • We will help you order the 3D Printed products with the 3D Printing bureau that best fits your needs.

    • Our production partners are in USA and EU, and serve globally.

    What you get:

    • Up to 3 design iterations

    • Ownership of the digital 3D file.

    • Printability guarantee

    • *cost of 3D printing is not included

    Approximate costs:

    As a solution-based studio, we understand that price greatly depends on complexity of the problem to be solved, nevertheless, our experience creating designs for 3D Printing, allows us to set a tiered-price, that works in most cases:

    3D Doctor:
    > 1000 €

    Projects where a 3D file is provided and needs minor tweaks to make it 3D printable (i.e Generate a valid geometry, thickness, hollow a model...)

    Sketch to 3D:
    > 5000 €

    Projects where a clear idea, style and dimensions of the final object is drafted and needs to be modelled specifically for 3D Printing.

    Concept to 3D:
    > 9000 €

    Projects where no prior design work has been done and ideation + design + modelling is needed.

    Read More
    Bernat Cuni Bernat Cuni

    Artificial Scarcity Store

    A daily creation, temporarily available for purchase.

    A random creation,
    temporarily available for purchase.

    Launched Today:
    - available for few days, until the next update.

    Too Late:
    - not available anymore

    What is this?

    This is a design.store, you can buy what has been launched today, and it will be shipped to your door, like any other online store. *here the details

    But beware, today’s item will be replaced by a new one tomorrow; and it won’t be available anymore, ever.

    All items are unique to this site, and exclusively deigned by Bernat Cuni.

    Mainly it is a store of things that can’t be bought, except for one.

    It is an ongoing experiment on design, digital fabrication, consumerism, globalisation, social networks & niche markets.

    The Artificial Scarcity Store is supposed to trigger different reactions:

    • Some, moved by a FOMO, might feel unconfortable knowing that today’s piece will become unavailable tomorrow.

    • Others, facing the paradox of choice, might feel uneasy with the thought that tomorrow’s piece could be better than today’s one, and are unable to make a decision.

    I’m thankful to you, the ones who get it.

    For me, the main driver is crativity.

    The Artificial Scarcity Store is a daily challenge where to place my whatevers and sidekick ideas turned into buyable items. The ultimate reason to make them temporarily available is to not clutter my headspace, and have less things to manage.

    Technically, I use a network of providers to fabricate and ship the goods.

    A design can be turned into multiple items:

    • if it is a graphic that gets printed on a product, I tend to use Society6

    • if it is a 3D model, I usually use Shapeways as a production partner, or I might post it on Sketchfab if it is an asset that could be used by other 3D developers.

    • If it is digital content, like a DesktopWallpaper or a 3D model, I host it locally at this site, or I might use pay-links to make a file downloadable.

    Nice?
    I hope you enjoy the Artificial Scarcity Store, contact for any question/comment.

    Store Details

    • Payments are securely processed and encrypted by Squarespace.

    • Delivery times is about 2 weeks (for US orders), add another week if ordering from the rest of the world.

    • Orders can be cancelled within 24h.

    • Customer service is a priority, if something goes wrong with the product we’ll try to solve it, and issue a partial or full refund accordingly.

    • All items are fabricated by 3rd parties.

    Read More
    Bernat Cuni Bernat Cuni

    XR Design

    AR/VR experiences for brands and custom projects

    Design for Mixed Reality

    Exploring AR/VR tools for creativity and augmented experiences.

    AR/VR projects brands and custom projects

    Tools & Platforms

    Augment your projects and make them available in multiple mediums.

    • iOS Ready - natively load 3D models and animations in AR

    • Unity - merge your content with a game engine

    • Dedicated Apps - enrich your project with a AR/VR app

    • Cross-platform - Oculus / Vibe / PlayStation VR

    Creation in VR.

    Experiment with the newest tools and creative software to create unique content.

    Screen Shot 2019-03-12 at 19.08.30.png

    Shareable

    Publish 3D content on webBased galleries

    Gallery

    Explore some of our models

    Read More
    Bernat Cuni Bernat Cuni

    3D Scan

    Creating a high detail digital archive of our material environment.

    Using multiple 3D scanning technologies we can create high detail digital copies of our material environment.

    HighRes scans for the creative industries, CGI, Gaming, AR/VR productions, educational content and cultural preservation.

    • High resolution texture maps,

    • HDLP - HighDefinition/LowPoly models: Manually retopologized from millions of polygons to an average of 5k-20k with HD NormalMaps.

    Computer Graphics Imagery (CGI) reigns most of the contemporary media. (Did you know that H&M uses digital female 3D models on their website? and that what you see on the IKEA catalog is digitally crafted? and that the food that appears on commercials is also 3D?).

    The omnipresence of CGI, combined with the rise of AR/VR platforms and the accessibility of 3D Gaming engines, creates the need for content.

    We (humanity) made lots of stuff to ta date, and now, that stuff can be digitally captured and archived for digital re-use.

    Some samples of models captured with photogrammetry:
    TreeBark scanned to design the TreeRing / here a making-of tutorial

    TreeBark scanned to design the TreeRing / here a making-of tutorial

    Read More
    Bernat Cuni Bernat Cuni

    Experiments

    Design & Software Solutions for Additive Manufacturing

    Design & Software Solutions for Additive Manufacturing

    Additive Manufacturing allows for creative fabrication of unique parts and prototypes.
    Designing specifically for this technology we can make impressive products suited for multiple applications.

    Example:

    meta.materials

    Designing material behaviour through internal structures.

    • Lightweight: Reduce volume.

    • Custom Performance: Variable density lattice.

    • Optimised for AM materials and manufacturing methods.

    Project Sample:

    Shock absorbing insole.
    Biometric data-driven variable density lattice structure.

    1. Design of a shock absorbing lattice structure.

    2. Populate the insole volume with the designed structure.

    3. Align the insole with a 3D scan of the wearer’s foot.

    4. Define the performance of the insole by selectively assigning different density to the lattice structure.

    Read More
    Bernat Cuni Bernat Cuni

    Permutation

    Generative collection, designed with code, 3D printed in Stoneware. 

    cunicode_permutation_stoneware_17.jpg

    Generative collection, designed with code, 3D printed in Stoneware.

    Pieces composed by the random combination of nine basic units, placed around a cylinder.

    Each piece is unique and exists within an immense landscape of millions of possible different combinations.

    • Material: Stoneware

    • Printed by: bcn3Dceramics

    • Software: Rhino3D / Grasshopper

    • Machine: PotterBot 3D printer

    • Design by: Bernat Cuni

    • Exhibited at: Argillà Argentona - International ceramics fair

    P114.3

    148.791.629.670.981.130.805.037.453.479.575.340 possible combinations.

    vaserenders.238.png

    One hundred and forty eight decillion, seven hundred and ninety one nonillion, six hundred and twenty nine octillion, six hundred and seventy septillion, nine hundred and eighty one sextillion, one hundred and thirty quintillion, eight hundred and five quadrillion, and thirty seven trillion, four hundred and fifty three billion, four hundred and seventy nine million, five hundred and seventy five thousand, three hundred and forty.

    P16.4

    66.305.137.490.523.096 possible combinations.

    vaserenders.236.png

    sixty-six quadrillion, three hundred and five trillion, one hundred and thirty-seven billion, four hundred and ninety million, five hundred and twenty-three thousand, one hundred and four

    Read More
    Bernat Cuni Bernat Cuni

    art.faces - AI sculpts 3D faces from famous paintings

    Exploration on face detection and 3D reconstruction using AI

    Exploration on face detection and 3D reconstruction using the "Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression" code by Aaron S. Jackson, Adrian Bulat, Vasileios Argyriou and Georgios Tzimiropoulos.

    link: https://www.cunicode.com/works/artfaces Using the demo from the paper "Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression", we let the AI sculpt 3D faces from famous artworks.

    We selected 8 Famous Paintings and let the Convolutional Neural Network (CNN) perform a direct regression of a volumetric representation of the 3D facial geometry from a single 2D image.

    01 Mona_Lisa,_by_Leonardo_da_Vinci,_from_C2RMF_retouched.jpg

    Mona Lisa

    Leonardo da Vinci
    c. 1503–06, perhaps continuing until c. 1517
    Oil on poplar panel
    Subject: Lisa Gherardini
    77 cm × 53 cm
    Musée du Louvre, Paris

    03 Meisje_met_de_parel.jpg

    Girl with a Pearl Earring

    Meisje met de parel
    Johannes Vermeer
    c. 1665
    Oil on canvas
    44.5 cm × 39 cm
    Mauritshuis, The Hague, Netherlands

    05 Sandro_Botticelli_-_La_nascita_di_Venere_-_Google_Art_Project_-_edited.jpg

    The Birth of Venus

    Nascita di Venere
    Sandro Botticelli,
    The Birth of Venus (c. 1484-86).
    Tempera on canvas.
    172.5 cm × 278.9 cm.
    Uffizi, Florence

    Las Meninas

    Diego Velázquez
    1656
    Oil on canvas
    318 cm × 276 cm
    Museo del Prado, Madrid

    02 Vincent_van_Gogh_-_Self-Portrait_-_Google_Art_Project.jpg

    Self-Portrait

    Vincent van Gogh
    September 1889
    Oil on canvas
    65 × 54 cm
    Musée d'Orsay, Paris.
    This may have been Van Gogh's last self-portrait.

    04 Cavalier_soldier_Hals-1624x.jpg

    Laughing Cavalier

    Frans Hals
    1624
    oil on canvas
    83 cm × 67.3 cm
    Wallace Collection, London

    06 Grant_Wood_-_American_Gothic_-_Google_Art_Project.jpg

    American Gothic

    Grant Wood
    1930
    Oil on beaverboard
    78 cm × 65.3 cm
    Art Institute of Chicago

    08 The_Nightwatch_by_Rembrandt.jpg

    The Night Watch

    Rembrandt van Rijn
    1642
    Oil on canvas
    363 cm × 437 cm
    Rijksmuseum, Amsterdam

    The technology behind: 

    Code available on GitHub
    Test your images with this demo,

    This tech is fantastic and amazing, but same as with DeepFakes, it should be handled with care… Once we can generate accurate 3D representations of anyone with minimal input data, there’s the possibility to use that 3D output as digital identity theft.

    As well questioned in this VentureBeat article : 

    So what happens when the technology further improves (which it will) and becomes accessible to marketers and brands (which it always does)? Imagine a casting call where a dozen actors are digitally and convincingly superimposed on a stand-in model prior to engaging the actors in real life.

    We can imagine a scenario where videos are created using someone’s face (and body?) to make them do whatever they want, without consent.

    On the other hand, AI is getting so smart, that in some cases, it doesn’t need a real input to go wild and imagine possible realities.

    In this paper by NVIDIA, a generative adversarial network is able to picture imaginary celebrities.

    Particularly in the 3D space, we see a huge potential for this kind of technology.

     

     

    Read More
    Bernat Cuni Bernat Cuni

    Digital Ceramics

    Ceramic 3D Printing products and services for the industry & the arts

    Ceramic Additive Manufacturing products and services for the Industry & the arts

    Powder Binding / SLA / Paste Extrusion

    Read More
    Bernat Cuni Bernat Cuni

    Tree Ring

    BUY NOW

    Made with data captured from a tree in a hiking trip at the french Pyrinees,
    digitally turned into a 3D log, and edited to become an ultranature ring.

    664155 polygons, generated via photogrammetry from 57 HQ photos of a real tree.

    Read More
    Bernat Cuni Bernat Cuni

    3D Scan / cultural heritage

    12th Century Capitals 3D scanned & released.

    Capturing architectural details with photogrammetry.

    12th Century Capitals 3D scanned & released.

    Capitell Arnau Cadell @ Monestir de Sant Cugat

    capitell.jpg
     
    Read More
    Bernat Cuni Bernat Cuni

    Flint, Hive & Bubbles

    A generative 3D Printed ceramic tableware.

    One design, unlimited variations.

    Designed with Symvol for Rhino for Uformit.
    DESIGN YOURS:
    Read More
    Bernat Cuni Bernat Cuni

    nicetrails

    Nicetrails was a service to turn GPS tracks into tiny mountains, 3D Printed - discontinued

     

    Turn GPS trails into tiny mountains, 3D Printed

    nicetrails.com is a tool for anyone to visualize and share gps-geolocalized data in 3D.

    EOL / 2016-2022

    nicetrails service is discontinued.

    We started this project in 2016 building a custom software to turn GPX tracks into 3D-printable files; now, in 2022 the internet has changed, and nicetrails should update its web usability and engine speed… but our focus is currently in another directions… so, discontinuing seems like a good choice now.

    Shutting down is a bit sad, but we enjoyed the journey.

    Thanks for your support during all this time.

    Bernat / designer
    Oscar / developer

    Website Archive

    Backend Archive / 3D engine / interface

    Some models created

    Alternatives

    Here some alternatives to keep turning GPS to 3D:

    Read More
    Bernat Cuni Bernat Cuni

    Window Shopping

    Capturing & Releasing

    Test: Street scanning + home 3D printing

    Capturing & Releasing

    Test: Street scanning + home 3D printing

    Made with 123DCatch | MeshMixer | MeshLab | Netfabb | Cura | Ultimaker 
    Get yours @Thingiverse

    Read More
    Bernat Cuni Bernat Cuni

    3D Printed Figurines from Children’s Drawings

    CrayonCreatures
    A service to turn wonderful drawings into awesome figurines; nice looking designer objects to decorate the home and office with a colorful touch of wild creativity.

    CrayonCreatures.com / (discontinued)

    Turning children’s drawings into 3DPrinted figurines.

    Crayon Creatures

    Children drawings are weird and beautiful.Kids produce an immense amount of drawings that populate fridges, living rooms and workspaces of parents, family & friends.Those drawings are amazing.

    Now you can turn those drawings into volumetric figurines; nice looking objects that will decorate your home and office with a colorful touch of wild creativity.

    http://CrayonCreatures.com will bring to life the kid’s artwork by 3D modeling a digital sculpture and turn it into a real object using 3D Printing technology.

    The figurines are custom designed and digitally crafted one by one.
    Material: full color sandstone | Size: about 100mm tall.

    End of Life / 2013-2023

    Read More
    Bernat Cuni Bernat Cuni

    One Coffee Cup a Day | 30 days, 30 cups

    One Cup a Day project is an experiment on creativity and rapid manufacturing, by ideating, designing, modeling and making available for production and purchase a coffee cup within 24 hours, everyday during one month.

    One Cup a Day project is an experiment on creativity and rapid manufacturing,
    by ideating, designing, modeling and making available for production and purchase a coffee cup within 24 hours, everyday during one month.

    All Cups

    By the end of each day, a new espresso coffee cup was made be available for sale here.
    The cups are printed in Glazed Ceramics by Shapeways & i.Materialsie.

    *the following images are computer generated visualizations of the cups, not the actual objects.
    As 3D-printing in ceramics is a novel and experimental process, the 3D-printed cups might look different than the images below.

    DIY REPRAP print

    Design one yourself

    This project is open for collaboration,
    Here I make available the source files (as .STL & .IGS files of a template basic cup,
    please, feel free to play around and modify it.

    3D Print it yourself

    The OctoCup is shared at Thingiverse, feel free to grab the files, experiment with it and share the results.
    I printed one with a RepRap and it looks nice, (useless, but nice).

    Learnings

    done! I made it; Design 30 cups in 30 days,

    They are all at the store, ready to be 3DPrinted on demand.

    Surprisingly, the idea generation has been the easiest part of the project,
    I still have tons of cup ideas on my head that  were not designed: (Banana Handle cup / Toilet cup / Matrioska cup / Melted cup / Mustache cup…)

    The hardest part of the project has been preparing the 3D geometries and files for 3DPrinting.
    The 30 designs can be grouped into 3 categories

    Morpho-jokes = cups adopting shapes from other contexts with a funny result.
    Uselessly nice = cups whose striking uselessness makes them interesting.
    Texture Analogies = cups wrapped by textures.

    I really enjoyed the project format, the challenge and the results.

    3D Model vs. 3D Print:

    The first 3DPrinted Cup in Ceramics just arrived,
    and it looks fantastic!

    The glazed layer is quite thick and it hides a lot of the original detail, which is OK for the OctoCup, but it might be a bit too soft for other designs, like the Knitted Cup or the LowResolution Cup.

    It has an overall look and feel of a hand-made product, which is very interesting, because this object was “untouched by humans” (except for finishing and shipping), meaning that it was designed in computer, with perfect radiusess, and perfect proportions, Then, it was 3DPrinted with a computer controlled machine accuracy, but the result is bumpy and imperfect, and it is nice.
    It almost feels like an craft object, but this cup is entirely a computer-born and grown object.

    Update: Shapeways improved their 3DPrinting process and the results are much better now.

    Notes

    About the design:

    The cups are designed as a creative exercise and as a proof of concept for digital fabrication, in order to achieve something unthinkable some time ago: Create a product from the idea to the consumer in less than 24 hours.

    Some designs are compromised due to time constrains, but that’s OK.

    Not all the cups are ment to be the best and most functional of all coffee cups ever, they are designed with style, fun and diversity on mind.

    About the material:

    The coffee cups are 3D Printed in Glazed Ceramics.
    Glazed Ceramics are food safe, recyclable and heat resistant.  The glaze is heatable up to 1000 degrees celcius, at which point the glaze will start to damage.

    3D Printed Glazed Ceramics material properties are exactly the same as standard ceramics as it is produced with fine ceramic powder which is bound together with binder, fired, glazed with lead-free, non-toxic gloss finish. For some designs with clear bottoms, the bottom side may remain unglazed.

    Glazing reduces definition of design details, for example grooves will fill with glaze. up to 1 mm of glaze can be added in certain areas.This means that some cups might look much smoother once printed than how they look on the drawings, keep that in mind if you purchase any of them.

    • Step 1. 3D Printing, it takes about 4 hrs to print a 4 inch piece. During this step, binder is deposited on a bed of ceramic powder. After one layer is done, a new layer of ceramic powder is spread on top and binder is again deposited on that layer.

    • Step 2. After all the layers are printed, the box of ceramic powder is then put in an oven to dry, the models in the box solidify during this process.

    • Step 3. After the models solidify, the models are taken out out of the box and depowdered. During this stage, the models are solid but in a brittle, fragile state.

    • Step 4. Afterwards, the models are fired in a kilm with a “high fire.” This firing will lock in the structure of the model. After this step, a base model is created. The surface finish is very rough.

    • Step 5. Pre-glaze coating spray, a water based spray, is then applied. Then the models are fired away in a kiln at a lower temperature. Afterwards, the model is a bit more smooth and ready for glazing.

    • Step 6. The glaze spray is applied, and the models are again fired in the kiln. After this process, the model becomes shiny and smooth.

    ​​Note to buyers:

    All cups are available for purchase here:  

    The cups are espresso size; about 65mm tall.
    They might look quite small.
    The images in this page are computer generated, not photos from the real cups.
    3DPrinting in Ceramics is a novel and experimental production process, the resulting objects might loose detail and look different than the above images.
    Production: Orders, payment, producing-printing, quality control, delivery & customer service processes is handled by     Shapeways.com, a 3rd Party Company not related to Cunicode.
    Pricing: 3DPrinting in Ceramics is quite expensive, that’s why the cups are very small, to keep the price down. Cunicode gets $5 per cup sold only, the rest goes to the producing company, 

    Further development

    Thanks for the interest and support,
    special thanks to ignant.de / Swiss-Miss / Neatorama / BoingBoing & others fantastic sites for writing about the project.

    Donate

    I'd like to 3DPrint all the cups and prepare an exhibition.
    Please contribute to make it happen.
    Thanks.

    Read More