Rui Xu

WE GOT THE BEST PAPER AWARD OF #SIGGRAPH2023!!! It's a great honor to receive this award. Our paper focuses on normal consistency, and obtains globally consistent normal vectors by regularizing the Winding-Number field. ✨I'm also actively looking for a PhD position!✨

Introducing ✨RigidFormer: Learning Rigid Dynamics with Transformers - our attempt to scale learning-based physical dynamics with Transformers. RigidFormer learns rigid dynamics with Transformers. It is a mesh-free, object-centric Transformer for multi-object rigid-body contact dynamics from point clouds. Learning physics with purely neural simulators, without relying on traditional physics engines, is an important and widely studied problem. Prior SOTA methods often use graph neural networks for accuracy and generalization, but still struggle with efficient, high-fidelity simulation at scale. RigidFormer uses only point inputs, matches or outperforms mesh-based baselines on standard benchmarks, runs much faster, generalizes across point resolutions and datasets, and scales to 200+ objects. We also show a preliminary extension to command-conditioned articulated bodies by treating body parts as interacting object-level components. RigidFormer is mesh-free: it does not require mesh connectivity, SDFs, or vertex-level message passing, making it well-suited for point-cloud observations and scalable simulation. This architecture can also be adapted to learn soft-body dynamics by replacing the rigid-body module (differentiable Kabsch alignment). 🎬See our video for more details. Many thanks to my amazing collaborators: Minghao Guo @GuoMh14, Haixu Wu @Haixu_Wu_1998, Doug Roble, Tuur Stuyck @TuurStuyck, and Wojciech Matusik @wojmatusik. Project page: people.csail.mit.edu/frankzydou/pro… Paper: people.csail.mit.edu/frankzydou/pro…

@real_kai42 爱您❤️

😯 cooooooooooooooooooool

🤯Topology & UV — the NO.1 headaches in #3D GenAI. 🔥We just move closer to BOTH at the same time. Introducing SATO: Strips as Tokens, a new autoregressive model for topology & UV, has been conditionally accepted to #SIGGRAPH 2026. Will available at #Hyper3D More details👇

@DeemosTech happy to release our latest work!

🚀 Excited to share our #CVPR2026 paper: EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents. EmbodMocap, a portable yet affordable solution requiring only two moving iPhones—no calibrated multi-view camera studio, motion capture suits, or LiDAR sensors needed. With our fully automated optimization pipeline, you can effortlessly obtain high-precision scene meshes, human interaction motions, RGBD images, and camera parameters. The captured data is ready for training human-scene reconstruction models (like TRAM, pi3, etc.) and humanoid control policies (like deepmimic, AMP, etc.). What you need to do: 1. Borrow or buy two iPhone 12 Pros from eBay (600 USD in total). 2. Find 2 friends, then capture the sequences. 3. Deploy our repo, run our code, and get the results! The code and data will be released within 1 week. (Just come back to work from the Chinese Spring Festival, Happy Chinese New Year!) 📷 Project page: wenjiawang0312.github.io/projects/embod… 📷ArXiv: arxiv.org/abs/2602.23205 📷Code: github.com/WenjiaWang0312…

We present EgoReAct: Real-time 3D human reaction generation from streaming egocentric video. 🌟Reacting to streaming egocentric video is something humans do every day. We hope EgoReAct makes human motion more human-like. 🔎 What we found: existing ego-reaction data can be spatially inconsistent (e.g., moving reactions paired with fixed-camera videos), which breaks 3D grounding. 📷 What we built: HRD, a spatially aligned egocentric video–reaction dataset (3,500 pairs, 32 categories), plus a spatially aligned ViMo fix for fair evaluation. (Instead of collecting expensive ground-truth motion, we employ VDM to generate the egocentric videos.) 👁️⚡🏃 Our simple yet effective pipeline: motion tokenization for compact discrete codes + an autoregressive Transformer for online, strictly-causal generation. Metric depth and head dynamics further improve 3D spatial consistency. Project Page: frank-zy-dou.github.io/projects/EgoRe… ArXiv: arxiv.org/abs/2512.22808 #HumanMotion #EgocentricVision #3D #ARVR #Animation #AIGC #DeepLearning #GenerativeAI #Graphics #ComputerVision #Motion

Check out 🌟Vid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry & Physics for Mesh-Free Simulation #CVPR2025, from @LingjieLiu1’s lab at UPenn. Congrats to @MorPhLingXD! Vid2Sim aims to achieve system identification by reconstructing geometry, appearance, and physical properties directly from video. It combines learned data priors with closed-loop optimization: a feed-forward predictor trained on physical prior, followed by fast refinement via Neural Jacobian and mesh-free simulation. The system delivers simulation-ready outputs in minutes, with strong generalization across objects and materials. 🏠Project page: czzzzh.github.io/Vid2Sim/ #PhysicalAI #AIGC #CV #CG #simulation #graphics

@real_kai42 包买 max 的，别的到时候都是红米

🤔 不懂车，在纠结 YU7 / pro /max - 我们驾驶风格比较保守 - 感觉正常家用，标准版就够，我们就自驾玩玩 - 但朋友说，四驱安全性 稳定性会好很多，下雨不容易打滑，或者一年能遇到一次的陷在泥里 - 大动力的意义是啥🤣（我真的不懂车），日常会用到么 - 以及，买 max 看起来也不会很贵，要不要为了豪华配置加钱。 毕竟随着年纪会对这些配置越来越无感，不如趁年轻奢侈一把 - “大佬直接送我辆车就不纠结了” 🐶

Cool

@lcMenci 确实🥲

作为一个 OI 圈的过来人，我觉得对着啥都说「羡慕」就相当于是当年的「我好菜啊」「您太强了」… 我不是想批判它，因为当年我也这样，但我想说，真的不是所有人都喜欢/接受这种风气。

SuperGaussians: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors @xrvitd, Wenyue Chen, @w080707, @YuanLiu41955461, @totoro97_, Lin Gao, Shiqing Xin, Taku Komura, Xin Li, Wenping Wang arxiv.org/abs/2411.18966

#SIGGRAPHASIA #SIGGRAPHASIA2024 #ACMTOG 🐟 We introduce Collective Behavior Imitation Learning (CBIL), a scalable, self-supervised framework for learning fish schooling behaviors from videos, to be presented at SIGGRAPH ASIA 2024 Tokyo (journal track)🗼! 🦈Reproducing realistic collective behaviors presents a captivating challenge, as traditional rule-based methods fall short in realism, while data-driven approaches rely on hard-to-acquire motion trajectories. 🐠CBIL first leverages a Masked Video AutoEncoder (MVAE) to map 2D observations to expressive latent states. Then an adversarial imitation learning framework with bio-inspired rewards is developed for stable and realistic motion generation. We demonstrate CBIL's effectiveness across various fish body shapes and its capability to detect abnormal behaviors from in-the-wild videos (real2sim4real). I like this attempt to “inject data priors” for Visual Imitation Learning, especially given the challenges of obtaining ground truth 3D motion for imitation. A heartfelt thanks to our amazing intern, Yifan Wu @Littlecobbler! Always remember the excitement we felt during those sleepless nights! And special gratitude to our incredible collaborators: Yuko Ishiwaka, Shun Ogawa, Yuke Lou, Wenping Wang, @LingjieLiu1, and Taku Komura. 🏠Project Page: frank-zy-dou.github.io/projects/CBIL/… 📑Paper: ACM Transactions on Graphics dl.acm.org/doi/10.1145/36… #AI #ImitationLearning #Animation #Animation #AI #CrowdAnimation #BehaviorAnalysis #CrowdMotion #Graphics #CG #Motion #AIGC #MotionSynthesis We showcase real-world videos and synthesized results, aligned for clearer visualization (rather than as reconstructions).

@frankzydou 你好，脑子借我

I accidentally hit my head while traveling, so I went for an MRI scan to check my brain. Fortunately, everything turned out fine. It was my first time seeing my brain 🧠. Hello, brain—or should I say, hello to myself!

@monday_chen @real_kai42 确实，所以我菜🥲

@real_kai42 @xrvitd 不是，独立完成也得搞版本管理啊，不然代码有问题要回滚咋浓

什么叫做滤镜破碎时刻 🐶 昨天帮 xr 迁移 blog （ruixu.me）仓库，如果你没听过他 @xrvitd ，他是大陆第一个图形学顶会 best paper 一作。 前面一顿操作之后，我说接下来，你把你本地 git 的 origin remote 移除掉，然后添加新的 origin，然后 push 就搞定了。 xr ：“啥？咋搞” 我：“你 git 不熟么” xr：“独立科研人都是自己完成所有代码🐶” 乐，在此之前，作为跟 xr 打桌游从来没赢过的我，一直以为他无敌，现在好了，跟朋友们有新梗了 《重生之，我教 SIGGRAPH Best Paper 学 Git》

@real_kai42 独立科研人！💪

wonderful opportunity!

Exciting news! 🌟 #SIGGRAPHAsia2025 will be held in #HongKong at #HKCEC! With #SIGGRAPHAsia2024 in Tokyo set for success, we look forward to dynamic innovation in both cities. See you there! 🗓Save the dates! Tokyo: 3-6 Dec'24 @ TIF + Hong Kong: 15-18 Dec'25 @ HKCEC! #HKTB #MEHK

1/ Happy to share our new paper "Surface-Filling Curve Flows via Implicit Medial Axes" at #SIGGRAPH2024! We introduce a fast, robust and user-controllable algorithm to compute surface-filling curves. 🐍✈️ dgp.toronto.edu/projects/surfa…

Our Surf-D is accepted at ECCV 2024 @eccvconf. Codes are released. Surf-D can generate arbitrary typology shapes in high resolution using UDF representation. Project page: yzmblog.github.io/projects/SurfD/ Arxiv: arxiv.org/abs/2311.17050 Codes: github.com/Yzmblog/SurfD #eccv #SurfD

@suxb201 快发我列表康康

朋友找了一批龙傲天动漫，一起品鉴，每部只看第一集😆