Graphics and Extended Reality Team (GERT) @GERTGraphics

Introducing EgoVerse: an ecosystem for robot learning from egocentric human data. Built and tested by 4 research labs + 3 industry partners, EgoVerse enables both science and scaling 1300+ hrs, 240 scenes, 2000+ tasks, and growing Dataset design, findings, and ecosystem 🧵

Newton 1.0 is now generally available. 🙌 Take robot learning to the next level with: 🤖 Stable Articulated & Complex Mechanism Simulation – accurate, reliable machine modeling. 🖐️ High-Fidelity Hydroelastic Contact Modeling – realistic soft contact and touch-based interactions. 🧵 Deformable Body Simulation – simulate cables, cloth, rubber, and other elastic materials with VBD. ⚡ Accelerated Robot Learning at Scale – seamless integration with open simulation and learning frameworks, NVIDIA Isaac Sim and Isaac Lab for scalable workflows. Learn how to integrate this open-source physics engine into your workflow: nvda.ws/3NGTzUo #NVIDIAGTC

Physics-Based Simulation v1.0.3 is now live! phys-sim-book.github.io This release features @zzigakovacic's awesome coding examples on MPM viscoplastic flow, PBD cloth and elastic bodies, and PBF! Huge thanks to all! #Physics #Simulation #Animation #ComputerGraphics #MPM #PBD

coordinating 102 muscle actuators to move 126 neo-Hookean tetrahedra

In this proof-of-principle study, brain activity was recorded in children aged 3–5 years as they chose and interacted with human-like avatars.

Free and open source markerless motion capture of a runner on a treadmill! Reconstructed from 6 webcams using FreeMoCap v1.7.2 #freemocap #blender #motioncapture #mocap #animation #biomechanics

Exploring the in-between with MLS-MPM, inspired by splash-fluid.netlify.app. Fluid behavior, jelly soul. Demo 👉 fluid02.sujen.co #threejs #webgl

Well done!

Industrial Light & Magic @ILMVFX

6 months ago

James Cameron on the original #Avatar prototype created by ILM and how their achievements on Fire and Ash pushed the series into a new age. Catch the full interview on @TheMoviePodcast feed and YouTube. Avatar: Fire and Ash is now playing exclusively in theatres.

0 16 109 7K 17

🚀 Newton Beta 2 and roadmap to 1.0 is out. SDF-based collisions & hydroelastic contacts for manipulation, cable-type deformables in VBD solver, stronger MuJoCo Warp integration and a new L-BFGS optimizer for IK solver are among major features of Beta. github.com/newton-physics…

Disney Research shared a new look at the Olaf animated character, included a closer look at the inner workings of the robot, walk cycle, impact reductions, and how they track the character's performance.

Disney olaf robot. Classic mimic RL with nice modelling. Surprisingly small legs and big necks.

keyboard_arrow_left Previous keyboard_arrow_right Next

We are so excited when other people build strong models. It's great for the field and great for NVIDIA. That's why we're developing Nemotron openly. I can't wait to see what Marin does next!

Percy Liang @percyliang

6 months ago

This is not just another strong open model. Nemotron actually releases training data (!), RL environments, and training code. This is a big difference: almost all model developers just want people to use their models; NVIDIA is enabling people to make their own models. We are

31 181 2K 158K 607

Video diffusion models have strong implicit representations of 3D shape, material, and lighting, but controlling them with language is cumbersome, and control is critical for artists and animators. GenLit connects these implicit representations with a continuous 5D control signal describing the direction and intensity of a point light source. This enables single-image near-field relighting of an image using a video diffusion model. We use a ControlNet-like approach and show that, with a small amount of synthetic data, GenLit generalizes to complex real-world images. Given a single image and the 5D lighting signal, GenLit creates a video of a moving light source that is inside the scene. It moves around and behind scene objects, producing effects such as shading, cast shadows, secularities, and interreflections with a realism that is hard to obtain with traditional inverse rendering methods. GenLit shows that it is possible to get continuous control over implicit physical processes within a video model. I think this is just the beginning and promises to make such models much more practical for creators. @sbharadwaj__ will present today at SIGGRAPH Asia Room: S423/S424, Level 4 @ 13:50 on 15 of Dec. genlit.is.tue.mpg.de

How does the time- and shear-dependent viscosity influence the jet breakup intensity? See our recent paper doi.org/10.1016/j.ijmu…. Video: Gas-liquid interface colored by the structural integrity of the thixotropic fluid during primary breakup.

I built and ran these demos after @milesmacklin pointed me towards them during a conversation and I was blown away. worth watching this video and if you can actually playing with the demos / code. youtube.com/watch?v=cGemwD…

📣TEACHERS - Do you teach or support neurodiverse students? We’d love to hear from you! We’re exploring how to make the micro:bit and @MSMakeCode experience even more accessible for neurodiverse learners — and your insight can help guide this work. 💚

Good summary of our paper on neural physics - fine tuning learned simulators on real world data is indeed a key motivation. Another nice property is that now your physics engine can run on Tensor Cores and can benefit from all the hardware NVIDIA develops to make LLMs go fast.

Lucky Iyinbor @Luckyballa

8 months ago

Why would anyone need «neural physics»? Well, at least one problem it solves is the sim-to-real gap, and that’s what this paper is about NeRD is a neural simulation module that can predict future states of articulated rigid bodies, completely replacing time integration and

keyboard_arrow_left Previous keyboard_arrow_right Next

1 17 113 24K 90

Ep. 1 of Lab Tech with Teddy 🧸🧠 Meet EEG — a safe, playful way we study brain activity in babies & toddlers. Making developmental science fun + accessible 💡 #ChildDevelopment #BrainDevelopment #ScienceCommunication

🚀We have PhD openings in my lab at TU Munich! Explore 3D/4D reconstruction & generation, semantic & functional understanding, and more - at the intersection of graphics, vision, and machine learning. 💼PhDs are 100% E13 positions 👉Apply: 3dunderstanding.org/openings.html or via ELLIS!