This is the medical team from Wuhan responsible for recovering 50K+ patients in just a few months. They're now risking their lives again to help out Italy. Rag on China all you want for the mishandlings early on but you can't deny that these people are true selfless heroes.

Smoothly switch between CPU, GPU, and TPU; between single-card, multi-card, and many-many-card? Computing normals, curvatures, gradient-of-gradient-of-gradient of your NeRFs without pain? In JaxNeRF, it works!

If what NeRF did was "cool", then having a NeRF-like model which you can re-light and render in a graphics-y way is, as Quentin said(youtu.be/qfnP-QYaEoo?t=…), "suba cool"! And that would be NeRV.

Thanks to Frank, we now have an all-in-one article for anyone who wants to learn NeRF from scratch. I always hope there's a roadmap like this for new things I'd like to learn. So everyone, more like this, please :-)

#Oscars Moment: Chloé Zhao accepts the Oscar for Best Directing for Nomadland.

NeRFactor is out! It's a physically-based model that factorizes appearance into shape and reflectance given just multi-view images under *one unknown* illumination (i.e., NeRF data). It supports free-viewpoint relighting (w/ shadows!) and material editing. bit.ly/3uR6e7Q

Introducing Proteus 0.1, REAL-TIME video generation that brings life to your AI. Proteus can laugh, rap, sing, blink, smile, talk, and more. From a single image! Come meet Proteus on Twitch in real-time. ↓ Sign up for API waitlist: apparate.ai/early-access.h… 1/11

Symmetries are everywhere — from butterfly’s wings to Greek temples. But detecting them in noisy data? That’s a challenge. 🦋🏛 Our #SIGGRAPHAsia2024 paper, Robust Symmetry Detection via Riemannian Langevin Dynamics, tackles this: symmetry-langevin.github.io 🧵(1/n)

🚀 Introducing CAT4D! 🚀 CAT4D transforms any real or generated video into dynamic 3D scenes with a multi-view video diffusion model. The outputs are dynamic 3D models that we can freeze and look at from novel viewpoints, in real-time! Be sure to try our interactive viewer!

Introducing 👀Stereo4D👀 A method for mining 4D from internet stereo videos. It enables large-scale, high-quality, dynamic, *metric* 3D reconstructions, with camera poses and long-term 3D motion trajectories. We used Stereo4D to make a dataset of over 100k real-world 4D scenes.

Introduce CoT-VLA – Visual Chain-of-Thought reasoning for Robot Foundation Models! 🤖 By leveraging next-frame prediction as visual chain-of-thought reasoning, CoT-VLA uses future prediction to guide action generation and unlock large-scale video data for training. #CVPR2025