A self-contained, portable implementation of Adobe's OpenPBR 1.0 BSDF github.com/adobe/openpb...
09.03.2026 20:53
๐ 28
๐ 4
๐ฌ 1
๐ 0
A self-contained, portable implementation of Adobe's OpenPBR 1.0 BSDF github.com/adobe/openpb...
"My motto is: just do it!" We love this interview w/ Maren Nattermann, Research Group Leader @ Max Planck Institute for Terrestrial Microbiology, on Marjory Stephenson (1885โ1948), pioneer of chemical microbiology as well as her own path into science www.mpg.de/26210626/mar... #IWD2026
This year at GDC, my peers Evan, Kelsey, and Richard will showcase the latest progress in the UE NvRTX branch, including LSS optimized hair strands path tracing, an area Iโve had the privilege to work on over the past couple of months.
schedule.gdconf.com/session/stat...
Love it!! ๐คฃ
What a delight.
Huge congratulations and shoutout to the @meshcapade.com team for bringing EPIC Games to Tรผbingen!!! This is very exciting. Iโm very fortunate to have @michael-j-black.bsky.social as my advisor. He is very inspiring and has a strong vision.
I agree. I especially find it unsettling when the said LLM validates our questions by saying โthatโs a great questionโ.
I love it so much. Lens flare!
Announcing SGI 2026! Undergrads and MS students: Apply for 6 weeks of paid summer geometry processing research. No experience needed: 1 week tutorials + 5 weeks of projects. Mentors are top researchers in this emerging branch of graphics/computing/math. sgi.mit.edu
Introducing CHORD, a universal framework for generating scene-level 4D dynamic motion from any static 3D inputs.
It generalizes surprisingly well across a wide range of objects and can even be used to learn robotics manipulation policy!
Project page: yanzhelyu.github.io/chord.
a ๐งต: 1/n
Doesnโt the center of mass of the bird change quite significantly due to its beak length? Itโs fascinating. The way it has evolved.
cseweb.ucsd.edu/~tzli/novelt...
I gave an internal talk at UCSD last year regarding "novelty" in computer science research. In it I "debunked" some of the myth people seem to have about what is good research in computer science these days. People seemed to like it, so I thought I should share.
Interesting post, working through and improving the performance issues of an LLM-generated IBL implementation: technik90.blogspot.com/2025/12/ibl-...
The red eye with the blue feathers. What a contrast!
I am attending Siggraph Asia at Hong Kong next week. I will be presenting GenLit: genlit.is.tue.mpg.de! Reach out to me if you would like to grab a coffee and chat about modelling illumination, spatial intelligence, and where we are headed as a community.
Excited to be at #Neurips2025 this week to present our paper "Monoculture or Multiplicity: Which is it?", joint work with Moritz Hardt.
๐ Paper #1000: openreview.net/pdf?id=DO5Lt...
๐ Wed, Dec 3, 2025 โข 4:30 PM โ 7:30 PM
Feel free to come by and reach out!
A short ๐งต.
Two black-and-yellow birds perched on a barbed wire fence against a soft green background.
#BirdoftheDay is #birdonawire x2
This male and female Black-headed Trogon were taking a break from digging out their nest cavity and posed for me.
#CostaRica #birds #nature
Here's a great video explaining/showing why the common CG practice of plugging smudge/fingerprints/dirt/whatever maps into roughness is wrong and why it should be done using material layering instead. This video is really well-made!
www.youtube.com/watch?v=OW4L...
@michael-j-black.bsky.social @saidwivedi.in @shrishabharadwaj.bsky.social Max Planck Institute for Intelligent Systems, Tรผbingen
Our Principal Investigators Antonio Orvieto, Celestine Mendler-Dรผnner, Maximilian Dax, Rediet Abebe, @shiweiliu.bsky.social, T. Konstantin Rusch, and @wielandbrendel.bsky.social are looking for motivated students interested in internships.
Apply here: docs.google.com/forms/d/e/1F...
โEveryone knowsโ what an autoencoder isโฆ but there's an important complementary picture missing from most introductory material.
In short: we emphasize how autoencoders are implementedโbut not always what they represent (and some of the implications of that representation).๐งต
Just the right amount of weird! Amazing fast forward video!! ๐๐ผ
Differentiable rendering has transformed graphics and 3D vision, but what about other fields? Our SIGGRAPH 2025 introduces misuka, the first fully-differentiable path tracer for acoustics.
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. ๐ณ๏ธโโง๏ธ๐ณ๏ธโ๐
docs.google.com/document/d/1...
Here are all the CVPR projects that Iโm part of in one thread.
Conference papers:
PromptHMR: Promptable Human Mesh Recovery
yufu-wang.github.io/phmr-page/
DiffLocks: Generating 3D Hair from a Single Image using Diffusion Models
radualexandru.github.io/difflocks/
๐๐ฒ๐ป๐ฒ๐ฟ๐ฎ๐๐ถ๐๐ฒ ๐๐ฒ๐๐ฎ๐ถ๐น ๐๐ป๐ต๐ฎ๐ป๐ฐ๐ฒ๐บ๐ฒ๐ป๐ ๐ณ๐ผ๐ฟ ๐ฃ๐ต๐๐๐ถ๐ฐ๐ฎ๐น๐น๐ ๐๐ฎ๐๐ฒ๐ฑ ๐ ๐ฎ๐๐ฒ๐ฟ๐ถ๐ฎ๐น๐
Saeed Hadadan, Benedikt Bitterli, Tizian Zeltner ... Matthias Zwicker
arxiv.org/abs/2502.13994
Trending on www.scholar-inbox.com
Insane!
How can LLMs help computers see, how human motion is the dark matter of computer vision, what's artificial good-enough intelligence, & more? With Ben Kaplan at Deep Venture Partners.
@meshcapade.com @mpi-is.bsky.social
APPLE: lnkd.in/ez8cKuNs
SPOTIFY: lnkd.in/eWtmtHd5
Here's a link to a recent talk that I gave at the University of Aukland Bioengineering Institute, entitled "Pixels to Skeletons: Towards Internet-Scale Biomechanics." t.co/c1LODMUL5t
I have switched from X and Facebook to Bluesky. I will delete both my X and Facebook accounts in a little bit.
