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

Indeed Unreal Engine is moving to Left-Up-Forward coordinates everywhere, starting with UEFN, and coming to UE5-6 in an incrementally-adoptable way through UI settings and C++ helper functions/macros to ease the transition. This will align Unreal with Y-Up, right handed

⭐️PartCrafter jointly generates multiple parts from a single RGB image in one shot with 40s. The core philosophy driving our work is that "the best way to understand is to create". 🌐wgsxm.github.io/projects/partc… 📂 github.com/wgsxm/PartCraf… Stay tuned for exciting updates! 🎉

Thrilled to share the project we’ve been working on for the past year! Liquid Glass is a flexible material that constantly adapts to its size and environment, and lays the foundation for a unified design language across all our platforms.

Our #SGP25 work studies a simple and effective way to uniformly sample implicit surfaces by casting rays. (1/9) “Uniform Sampling of Surfaces by Casting Rays” w/ Abhishek Madan Nick Sharp Alec Jacobson

💫It's fascinating that a single feed-forward pass through an LLM can replace a complex rendering pipeline, like Blender! Just feed it 3D shapes, xyz positions, and poses as tokens, and it spits out the image token-by-token. The dual, aka scene reconstruction, is also

The Tanks have arrived in DC. Surreal.

我做「毛玻璃」也有一年多了，不得不站出来为Liquid Glass说句公道话：大家不要小看毛玻璃的意义，它不是为了好看，而是GUI软件为了支持多模态AI和AR/MR而从屏幕发展到空间计算所必然带来的重大本质变化😆 空间计算环境下，GUI的背景是真实物理空间，会动态变化和风格不一致、各种明暗各种颜色都有，

🚀 We just open-sourced Cosmos DiffusionRenderer! This major upgrade brings significantly improved video de-lighting and re-lighting—powered by NVIDIA Cosmos and enhanced data curation. Released under Apache 2.0 and Open Model License. Try it out! 🔗 github.com/nv-tlabs/cosmo…

🚀 Hunyuan 3D 2.1 is here! The first fully open-source, production-ready PBR 3D generative model! ✅Cinema-grade visuals: PBR material synthesis brings leather, bronze, and more to life with stunning light interactions. ✅ Fully open-source: Model weights, training/inference

🖌️ Rodin Gen-2 Quad Mode: One Click 🆚 👨‍🎨 Human Artist: 5 Hours of Work Can you tell which one is AI and which one is from a human? 🤔💭 Tell us how you figure out!

A failed replication! Lol, when I see Apple's spatial scene on WWDC25, I try to guess how they make it and attempt to create a pipeline to achieve a similar result. I used DepthPro from Apple and used AdaMPI (github.com/yxuhan/AdaMPI) from my friend Yuxuan, but the result is not

Technical artists: Is there any mathematical formula that can tell whether a normal map is OpenGL or DirectX format? It's crazy that in 2025 users are still guessing.

Wrapped up Stanford CS336 (Language Models from Scratch), taught with an amazing team Tatsunori Hashimoto Marcel Rød Neil Band Rohith Kuditipudi. Researchers are becoming detached from the technical details of how LMs work. In CS336, we try to fix that by having students build everything:

Very happy to receive a #SIGGRAPH2025 Best Paper Award (Honorable Mention) for our RSP algorithm, which dices surfaces into near-perfect rectangles. Such meshes are useful for everything from retopology, to microfluidic simulation, to textile design, to architectural geometry.

2/ Rerun isn’t “just a visualizer.” It’s the missing data stack for physical AI… used by teams at Apple, Meta, Google, and top robotics labs. But this episode isn’t about the tool. It’s about why Nikolaus West built it, and the journey that got him there. 🎧 Spotify:

Code dropped (Apache 2.0)! EX-4D: EXtreme Viewpoint 4D Video Synthesis via Depth Watertight Mesh The core of this framework is the Depth Watertight Mesh (DW-Mesh) representation, serving as a robust geometric prior to guide the video generation process. Unlike traditional

猎头哥们跟我说大厂搞大模型可能永远搞不过deepseek，因为kpi逼得人不求有功但求无过，攻坚新项目风险太高没必要去赌，这种傻事只适合创业公司all in。从这个视角来看华为的瓜，走捷径的人比苦哈哈的人混的好，劣币驱逐良币，一点也不意外。gemini和qwen堪称管理学奇迹，llama和siri才是常态。

🚀Introducing Hunyuan3D-PolyGen, our newly upgraded and industry-first art-grade 3D generative model. It brings effortless intelligent retopology, making AI-generated models ready for professional art pipelines. ✅ Superior Mesh Topology: Our self-developed mesh autoregressive

🚀 We release SpatialTrackerV2: the first feedforward model for dynamic 3D reconstruction and 3D point tracking — all at once! Reconstruct dynamic scenes and predict pixel-wise 3D motion in seconds. 🔗 Webpage: spatialtracker.github.io 🔍 Online Demo: huggingface.co/spaces/Yuxihen…