Hugging Face 🕍 Côté culture, nous lançons un projet de jumeau numérique de Notre-Dame de Paris avec le Ministère de la Culture 🇫🇷 et Iconem. Un monument emblématique, préservé pour les générations futures grâce à l’IA.

GitHub released Spark yesterday, their extremely well crafted prompt-to-app platform for creating and iterating on React apps with user auth and persistent storage I like it a lot! I reverse engineered it with Spark itself, the details are fascinating simonwillison.net/2025/Jul/24/gi…

100 open issues -> 22 open issues for Triplex! 👪 UI improvements to show relationships between elements in the element panel 🤏 Any element that has children in the element panel can now be collapsed 🫣 Much more! Keep reading! #threejs #reactjs #webdev #webgamedev

BIG NEWS! 📢 The PlayCanvas Editor Frontend is now Open Source! Read More: blog.playcanvas.com/playcanvas-edi…

できたっぽい > LightとLightNodeを作ってRendererのNodeLibraryに突っ込む。 これで本当に任意のマテリアルで、正確なライティングができる。これがこれまでのThree.jsのアーキテクチャだと難しかったんだよ！

#CesiumDevCon was a celebration of the accomplishments of the 3D geospatial community, a look into the future of developing digital twins, and a chance to hang out with hundreds of kindred spirits in Philadelphia. Session recordings are now available: hubs.li/Q03zJNg00

Vibecoded an animation timeline ui for threepipe, for automatic animations with configurators

Creating a digital twin of Notre Dame offers a unique opportunity to capture five years of extraordinary restoration and represents a lasting commitment to preserving the cathedral’s legacy for generations to come. Iconem Ministère de la Culture 🇫🇷 Microsoft euronews.com/next/2025/07/2…

Methods like NeRF and Gaussian Splats model the world as radioactive fog, rendered using alpha blending. This produces great results.. but are volumes the only way to get there?🤔 Our new SIGGRAPH'25 paper directly reconstructs surfaces without heuristics or regularizers.

US-French SWOT Satellite Measures Tsunami After Massive Quake ift.tt/HpEXiKx 4 min read Preparations for Next Moonwalk Simulations Underway (and Underwater) The SWOT satellite caught the leading edge of the tsunami wave (red) that rolled thr… ift.tt/ufVR3B8

Khronos, Open Geospatial: OGC, Niantic Spatial 🌎, Cesium, and Esri come together to add 3D Gaussian Splats to the glTF Asset standard! khr.io/1lp #Gaussian #splats #glTF

The threepipe editor is looking more and more like blender now, with eevee like rendering using webgi and cycles using three-gpu-pathtracer

Forgot to forward that thread for anyone interested!

[7/N] ViPE code is released at: github.com/nv-tlabs/vipe! Huge thanks to the incredible team behind this Qunjie Zhou Hesam Rabeti Aleksandr Huan Ling Xuanchi Ren Tianchang Shen Jun Gao Dmitry Chen-Hsuan Lin Jiawei Ren Kevin Joydeep Biswas Laura Leal-Taixe Sanja Fidler

Wow blown away by this demo by Alexandre Devaux! Nice and smooth, pretty impressed with what he achieved with opencv underlying calcOpticalFlowPyrLK and ORB keypoints running in-browser! The core beauty of it really resides in the fx created with the tracks once processed

Introducing DINOv3 🦕🦕🦕 A SotA-enabling vision foundation model, trained with pure self-supervised learning (SSL) at scale. High quality dense features, combining unprecedented semantic and geometric scene understanding. Three reasons why this matters…

Another SIGGRAPH exclusive Blender demo was Nvidia's DLSS denoiser for Cycles. It made moving around the viewport feel as smooth as EEVEE! Crazy stuff. Another video below

DINOv3 is revolutionary: a new state-of-the-art vision backbone trained to produce rich, dense image features. I loved their demo video so much that I decided to re-create their visualization tool. Everything runs 100% in-browser with 🤗 Transformers.js! Demo + source code 👇