Ruben Wiersma

9 July 2025

The materials of my graduate school course at #SGP2025 on "Deep Learning on Meshes and Point Clouds" are live on rubenwiersma.nl/deeplearning. A 'map' for 3D deep learning, covering the basics and thoughts on when and where to use deep learning tools in 3D.

Ruben Wiersma reposted

Ana Dodik

@anadodik.bsky.social

17 Aug

Charles Babbage intentionally designed the computer as an automation of mental labor. Today, computer graphics automates visual art production via privately governed generative models. How did we get here? Critical Labor History of Generative Models, SIGGRAPH Talks '26 🧵

youtu.beGradient Descent in the ALPS SIGGRAPH 2026 Fast ForwardYouTube video by Ruben Wiersma

20 July

ALPS: low-poly vector art for the low, low price of $0.00! CALL NOW at 1-800-GET-ALPS youtu.be/HZoWIM9_SD0 #SIGGRAPH fast forward

Ruben Wiersma reposted

Emilie Yu

@emxtyu.bsky.social

17 July

We're holding the Sustainable Graphics Birds of a Feather event again this year at #SIGGRAPH 🌱 please join us on Tuesday at 5PM (room 512)! This is a casual meet-up format open to anyone who's interested in the topic >> add to your schedule s2026.conference-schedule.org/presentation...

s2026.conference-schedule.orgPresentation - SIGGRAPH 2026 Conference Schedule

17 July

If you're coming to #SIGGRAPH, don't miss the 2026 Thesis Fast Forward in-person event! Recent PhD graduates will present their exciting thesis work on Monday 20 July from 10:30-11:30am in Room 404AB of the LA convention center: s2026.conference-schedule.org/presentation...

lnkd.inLinkedInThis link will take you to a page that’s not on LinkedIn

9 July

Yay, GravoTet received the best paper award at SMI! 🎉

Ruben Wiersma@rubenwiersma.nl

When we presented GravoMG, a fast multigrid solver for surfaces, the first question we got was: can you make this work for tetrahedral meshes? Tomorrow, Marcel Padilla will present the answer at SMI in Istanbul. Sneak preview: yes, it's really fast. Code and paper: marcelpadilla.com/Projects/Gra...

Plus: we show how you can preserve boundary elements well, which is especially important for problems tetrahedral meshes. Joint work with Tim Huisman, Jackson Campolattaro, Olga Sorkine-Hornung and Klaus Hildebrandt at @tudelfteemcs.bsky.social and @ethz.ch

Ruben Wiersma reposted

Alexandre Binninger

@alexbinninger.bsky.social

26 June

Replying to @alexbinninger.bsky.social

👉 Free for personal use: boldbobbin.com 👉 And if you want to shape what gets built next, come hang out in the Discord: discord.gg/wpnXsuxdkK I would love to know what you make! 🧵

boldbobbin.comBoldbobbin — The Modern Workspace for Embroidery DigitizingThe modern embroidery workspace in your browser or on your desktop.

Ruben Wiersma reposted

Nicole Feng

@nicole--f.bsky.social

15 June

I recently completed my PhD thesis, where I developed algorithms for making geometric inferences from imperfect data (i.e. incomplete and inaccurate observations/representations of shapes, like broken meshes or point clouds). A thread 🧵:

rubenwiersma.nl Ruben Wiersma · Computer Graphics, Art and ML Ruben Wiersma, Research Scientist at Adobe Research. My research topics include computer graphics, geometry processing and machine learning.

2 June

New job, new papers and some new creative projects. Time for an update of rubenwiersma.nl 🎉

@yiningkarlli.bsky.social

5 May

Having a wonderful time at the Eurographics Conference in Aachen! I gave the longest talk of my life (3h) on the biggest screen of my life and I received the Eurographics PhD award for my thesis 🎉 A huge thanks to @eurographicsc.bsky.social and all my collaborators and supporters!

Ruben Wiersma reposted

Yining Karl Li

3 Apr

I think this is a great article that puts to words something I've been thinking for a while about LLMs/AI/etc; as tools they clearly can be useful and are here to stay, but the real concern should be the effect it's having on the talent pipeline. (1/5) ergosphere.blog/posts/the-ma...

ergosphere.blogThe machines are fine. I'm worried about us.On AI agents, grunt work, and the part of science that isn't replaceable.

Ruben Wiersma reposted

Dr. Martin Skrodzki

@msmathcomp.bsky.social

12 Mar

Are you interested in #GeometryProcessing? Are you great with programming in C++? Are you a Master's/PhD student or a Postdoc? Then please apply for this project for the #GSoC. This is a great way to boost your portfolio while contributing to a widely used OpenSource library.

youtu.beSIGGRAPH Thesis Fastforward 2026YouTube video by ACMSIGGRAPH

23 Jan

The #SIGGRAPH Thesis Fast Forward 2026 is here! Learn about the future of CG in 9 PhD theses: from Monte Carlo PDE solvers and photorealistic 3D avatars to fantasy-based rehab games and modular umbrella meshes. 🎓✨ youtu.be/FlrTZEJeEXs

Ruben Wiersma reposted

youtube.comFast Forward SIGGRAPH 2025 - Uncertainty for SVBRDF Acquisition using Frequency AnalysisYouTube video by Ruben Wiersma

7 Oct 2025

The #SIGGRAPH Thesis Fast Forward 2026 submissions are now open! Deadline: Nov 7th 2025. Let the world know what you've been working on in your PhD! More info at research.siggraph.org/thesisff/ and check out last year's iteration youtube.com/watch?v=8esF...

Our fast forward for SIGGRAPH 2025. Keep SIGGRAPH weird! www.youtube.com/watch?v=sYel...

youtube.comUncertainty for SVBRDF Acquisition using Frequency Analysis - SIGGRAPH 2025YouTube video by Ruben Wiersma

18 Aug 2025

If you're confused, I uploaded the presentation as well www.youtube.com/watch?v=jv7o...

Ruben Wiersma reposted

s2025.conference-schedule.orgPresentation - SIGGRAPH 2025 Conference Schedule

30 July 2025

Mark your calendars for the #SIGGRAPH 2025 Thesis Fast Forward in-person event. Recent PhD graduates will present their thesis work and answer questions on Monday 11 August, 10:30-11:30am: s2025.conference-schedule.org/presentation...

Ruben Wiersma reposted

Emilie Yu

@emxtyu.bsky.social

4 Aug 2025

Replying to @emxtyu.bsky.social

If you are interested in joining a lively and supportive discussion space about sustainability & graphics research, please join our birds of a feather event on Tue Aug. 12 - 4PM, in East Building, Room 9 🌱 Co-organized with Felix Hähnlein, Chenxi Liu, Maria Larsson, and @rubenwiersma.nl

@anshulkundaje.bsky.social

30 July 2025

Ruben Wiersma reposted

Anshul Kundaje

17 July 2025

Fabulous post by @randomwalker.bsky.social & Sayash raising the same concern many of us have about whether we're on the right track with how we're using AI for science. Everyone should read it, take a deep breath & think through the implications. www.aisnakeoil.com/p/could-ai-s...

aisnakeoil.comCould AI slow science?Confronting the production-progress paradox

Simple idea to filter out (some) LLM-written papers with non-existent references: check the reference file agains DBLP and desk reject if a certain % of citations doesn't exist.

Friendlier implementation: add this as a check during submission and notify authors during submission + reviewers during review, similar to a plagiarism checks.

Simple idea to filter out (some) LLM-written papers with non-existent references: check the reference file agains DBLP and desk reject if a certain % of citations doesn't exist.

tinyurl.comWiGRAPH Conference Coffee: Sign-UpWiGRAPH is organizing a SIGGRAPH 2025 conference coffee! Are you a researcher of a gender that is underrepresented at SIGGRAPH? Would you like for an opportunity to network with peers? Sign up for th...

In an ideal world authors would not submit work they can't vouch for, but I've already heard multiple accounts of papers (under review and published) having non-existent citations. We also cannot expect reviewers to check this: automated writing scales, reviewer time has a limit.

Ruben Wiersma reposted

WiGRAPH

@wigraph.bsky.social

30 June 2025

🎉☕ Announcing WiGRAPH Conference Coffees: SIGGRAPH 2025 Edition! ☕🎉 Are you a researcher of an underrepresented gender registered for SIGGRAPH? Do you want an opportunity to network with your peers? Learn more and sign up here: www.wigraph.org/events/2025-...

If you have questions or feedback, I'd love to hear!

Ruben Wiersma reposted

Berend Baas

@berendbaas.nl

2 July 2025

Moving to sustainable manufacturing requires new computational design tools. We show how to make new objects from old "trash". 🚮 Presented on Thursday at SGP 2025 in the Fabrication session.

Ruben Wiersma reposted

David Levin

@diwlevin.bsky.social

18 June 2025

Holding SIGGRAPH Asia 2026 in Malaysia is a slap in the face to the rights of LGBTQ+ people. Especially now, when underrepresented people need as much support as we can possibly give them ! Angry like me ? Sign this open letter to let them know. 🏳️‍⚧️🏳️‍🌈 docs.google.com/document/d/1...

docs.google.comOpen Letter to the SIGGRAPH LeadershipRE: Call for SIGGRAPH Asia to relocate from Malaysia and commit to a venue selection process that safeguards LGBTQ+ and other at-risk communities. To the SIGGRAPH Leadership: SIGGRAPH Executive Commit...

github.comGitHub - rubenwiersma/painting_tools: Painting Tools and DatasetPainting Tools and Dataset. Contribute to rubenwiersma/painting_tools development by creating an account on GitHub.

11 June 2025

I'm sharing code&data of an unpublished project 🤯 During my PhD, I worked on applications of #computergraphics for #paintinganalysis. The main hurdle was the lack of #opensource code&data. I gathered my own, but didn't get to use it. Now I'm sharing it, so others can. 1/3 github.com/rubenwiersma...

11 June 2025

The dataset contains hyperspectral scans of nine reconstructions of historical paintings and ten historic pigments. The code provides tools to process and load this data and utilities to work with hyperspectral data (e.g., stitching scans, conversion to RGB). 2/3

@jcgt-announce.bsky.social

11 June 2025

My hope is that it finds use in research: technical art history, computer graphics, creative tools, etc. If you find a good usecase or are interested in collaborating, please reach out, I'd love to learn about it! 3/3

Ruben Wiersma reposted

JCGT announcements

6 June 2025

Annika Oehri, Philipp Herholz, and Olga Sorkine-Hornung, Higher Order Continuity for Smooth As-Rigid-As-Possible Shape Modeling jcgt.org/published/00...

Ruben Wiersma reposted

Emilie Yu

@emxtyu.bsky.social

1 June 2025

Ever wondered how badly we're all addicted to buying new GPUs in graphics labs? Come see our talk at #SIGGRAPH2025 to discuss how we can collectively move "Towards a sustainable use of GPUs in Graphics Research" with @elie-michel.bsky.social @axelparis.bsky.social Octave Crespel and Felix Hähnlein

8 May 2025

This was a wonderful collaboration 🤩 We developed a method that optimizes both an irregular tetrahedral grid and SDF for mesh optimization with marching tets. It recovers really detailed meshes with a fraction of the memory!

Alexandre Binninger@alexbinninger.bsky.social

🔷🦀 TetWeave: Isosurface Extraction using On-The-Fly Delaunay Tetrahedral Grids for Gradient-Based Mesh Optimization is accepted to #SIGGRAPH2025 (TOG). Done in collaboration with @rubenwiersma.nl, Philipp Herholz, and Olga Sorkine-Hornung. But why a new shape representation? (1/9)

4 May 2025

Has anyone else noticed a particular style to ChatGPT comics? I wonder if they sourced or synthesized a very ‘narrow’ dataset — or maybe it’s just confirmation bias on my end. The same for fonts.

30 Apr 2025

Recent progress in multi-view 3D object capture is stunning! But is there a limit? In our upcoming #SIGGRAPH2025 paper "Uncertainty for SVBRDF Acquisition using Frequency Analysis," we show how to answer this question for material estimation. 1/6

This gives us a practical measure of uncertainty that we use to 1. guide captures for better data, 2. share data between points, and 3. guide data-based priors in a diffusion model. 5/6

svbrdf-uncertainty.github.ioUncertainty for SVBRDF Acquisition using Frequency AnalysisWe quantify uncertainty for SVBRDF acquisition from multi-view captures using entropy. The otherwise heavy computation is accelerated in the frequency domain, yielding a practical, efficient method.

30 Apr 2025

A longer summary and the full paper are available on the project page: svbrdf-uncertainty.github.io. Special thanks to my collaborators @vdeschaintre.bsky.social, Julien Philip, Elmar Eisemann, Milos Hasan, Fujun Luan and Krishna Mullia! 6/6

How do we know when this is the case? In our paper, we use **entropy** to measure uncertainty. We argue (and show in our experiments) that where there is high entropy, we are more likely to have high error. 3/6

30 Apr 2025

Entropy can be expensive to compute. In our paper, we use frequency analysis to simplify and accelerate this computation. Our method takes 0.0005s, where it takes 6 minutes with a physically-based path tracer (Mitsuba), while still correlating strongly (0.9) 4/6

First, an example of uncertainty. In the image on the left, it is hard to tell a matte plane from a glossy plane, while it's clear on the right. In the first case, better algorithms will not give a better estimate, because the data is limited. 2/6