Our work RRM: Relightable assets using Radiance guided Material extraction was presented earlier this month at CGI2024 🌎in Geneva! Webpage: lix.polytechnique.fr/~gomez/RRM_web… 🧵 1/n

🎓The SIGGRAPH 2024 Thesis Fast Forward is happening on Monday at 1pm ! Come hear about recent graduates work and interact with them! s2024.conference-program.org/presentation/?…

Super excited to present our work ZeroGrads at SIGGRAPH 2024. Learn how ZeroGrads can differentiate ANY arbitrary graphics pipeline on Monday, in the 2pm "Differentiable Rendering" session, or check out the project page: mfischer-ucl.github.io/zerograds/

We’re thrilled to release the implementation and model weights for our SIGGRAPH 2024 paper, "RGB↔X: Image Decomposition and Synthesis Using Material- and Lighting-aware Diffusion Models"! 📂 GitHub Repository: github.com/zheng95z/rgbx RGB↔X is a unified diffusion-based

The code for our project *A Diffusion Approach to Radiance Field Relighting using Multi-Illumination Synthesis* is now available at: github.com/graphdeco-inri… Project Page: repo-sam.inria.fr/fungraph/gener… Thanks to the amazing work from Yohan Poirier-Ginter you can now relight your 3DGS!

DifFRelight: Diffusion-Based Facial Performance Relighting Fun fact: First 3DGS paper from Netflix! Contributions (cited): (1) A novel framework for facial performance relighting that trains on a subject-specific paired dataset and generalizes to novel lighting conditions,

Discover how cutting-edge diffusion models tackle relighting, harmonization, and shadow removal in this in-depth article on scene editing. Read more from darthgera123. #GenAI #MachineLearning towardsdatascience.com/let-there-be-l…

Wrote a blog about how diffusion models are being used to solve relighting tasks such as scene editing, harmonization, etc. Included papers from Chong Zeng Mengwei Ren He Zhang Matthias Niessner Jean-Francois Lalonde Yohan Poirier-Ginter Noah Snavely Haian Jin Peter Kocsis Julien Philip.

🎓 We introduce SAMa! A material selection and segmentation model on 3D models in any format (3DGS, NeRF, Mesh). Given a user click, we propose to select all regions on an objects with the same material. We can also do segmentation in under a minute: mfischer-ucl.github.io/sama/

Tomorrow in our TUM AI - Lecture Series with none other than George Drettakis. He'll talk about "𝐓𝐡𝐞 𝟑𝐃 𝐆𝐚𝐮𝐬𝐬𝐢𝐚𝐧 𝐒𝐩𝐥𝐚𝐭𝐭𝐢𝐧𝐠 𝐀𝐝𝐯𝐞𝐧𝐭𝐮𝐫𝐞: 𝐏𝐚𝐬𝐭, 𝐏𝐫𝐞𝐬𝐞𝐧𝐭, 𝐅𝐮𝐭𝐮𝐫𝐞". Live stream: youtube.com/live/DjOqkVIlE… 5pm GMT+1 / 8am PST (Mon Feb 3rd)

Splats are great, but wouldn’t it be wonderful if we could transform them into the stuff of dreams? Introducing our #CVPR2025 paper ✨Morpheus✨! Morpheus lets you change the shape and appearance of 3D Gaussian splats with a few words! nianticlabs.github.io/morpheus/ (1/6)

We present 𝘓𝘶𝘹 𝘗𝘰𝘴𝘵 𝘍𝘢𝘤𝘵𝘰! A Video Portrait Relighting method using Conditional Video Diffusion! To appear at #CVPR2025 ! Project Webpage: eyelinestudios.com/research/luxpo… Paper: arxiv.org/abs/2503.14485

We present 𝘓𝘶𝘹 𝘗𝘰𝘴𝘵 𝘍𝘢𝘤𝘵𝘰! A Video Portrait Relighting method using Conditional Video Diffusion! To appear at #CVPR2025 ! Project Webpage: eyelinestudios.com/research/luxpo… Paper: arxiv.org/abs/2503.14485

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

We cooked something exciting up for you! 🧑‍🍳 Your vision, brought to life: Transform any reference image(s) into videos exactly as you envision them and even star in them yourself. This has been so much fun to work on with an amazing team: Thomas Kipf, Serena Zhang, Yulia Rubanova,

#CVPR2025 is a wrap! Amazing contributions on lighting-related tasks this year. Now it’s time to look ahead to #ICCV2025 in beautiful Hawai’i. Let’s keep the momentum going and join us to explore and discuss how to evaluate lighting across diverse tasks!

Checkout our new SIGGRAPH Asia 2025 paper: repo-sam.inria.fr/nerphys/editab…. For more details see linkedin.com/posts/george-d…