
3D geometry researcher: graphics, vision, 3D ML, etc | Senior Research Scientist @NVIDIA | running, hockey, baking, & cheesy sci fi | opinions my own | he/him
Seattle, WA
Joined May 2018
- Tweets631
- Following347
- Followers6.3K
- Likes1.8K
Pinned Tweet
Giant new v1.2 release of Polyscope! Adds support for tet & hex meshes, transparency, ground shadows, slice planes, variable-size points, setting camera views, and more.
Try Polyscope for easy 3D visualization in C++ & Python: polyscope.run/
Thread of new features! 1/n
The Eurographics 2027 State of The Art Report submission deadline is in 11 days! (abstracts in 5)
STARs survey of a subarea in computer graphics, to summarize, taxonomize, and benchmark. They're hugely important and highly-cited. Submit your surveys!
eg2027.isti.cnr.it/call-for-…
Nick Sharp retweeted
In this era of artificial intelligence, it is becoming urgent to distinguish human art from what machines produce. There is an ontological difference, even before an aesthetic one, between art and what a machine can generate through statistical calculation based on millions of images created by others. Algorithms lack the spark of humanity. For this reason, the Church wishes to renew an alliance with artists and cultural institutions to safeguard our humanity.
Nick Sharp retweeted
The era of Physical AI is coming, and I firmly believe that embodied intelligence will not emerge from imitation learning alone. Just as humans first learn by observing the world and then build deeper understanding through interaction, the breakthrough moment for Physical AI will come through interactive learning.
Real-world trial and error is too slow, expensive, and unsafe. To scale interactive learning, we need to recreate the richness of reality without being constrained by reality itself. We need simulated reality—a place where embodied intelligence can experience situations, make mistakes, learn from them, and try again millions of times before encountering them in the real world.
I am incredibly excited to build @VeedaAI alongside my co-founders, @FidlerSanja and @HuanLing6 , and an extraordinary group of researchers and engineers. Together, we are developing the next generation of interactive foundation world models for Physical AI.
There is no team I would rather take on this challenge alongside, and I couldn’t be more excited for what we’re going to build.
veeda.ai
I’m incredibly excited to introduce @VeedaAI , which I co-founded with my incredible longtime collaborators @ZGojcic and @HuanLing6 .
We started Veeda because we believe robotics will reshape the world—changing how we move people and goods, how we manufacture and build, and how we operate in the physical world.
We also firmly believe that the scaling moment for Physical AI will come from robots learning through interaction with the world.
Just like humans learn from interaction with their environments by trying, failing and trying again, until we succeed. And just like the capabilities of LLMs were truly unlocked when they started training in interactive environments and not only on vast amounts of internet text.
For Physical AI, the central challenge is making this kind of interactive learning possible at scale. The real world is simply not a practical training ground for robots to learn through trial and error. It is unsafe, expensive, and time-consuming. To scale interactive learning, robots will need to learn in simulated reality.
At Veeda, our sole mission is to build simulated reality for Physical AI. Our conviction is that this will become the critical infrastructure layer for all areas of robotics.
As envisioned in pop culture, this means building “the Matrix” for Physical AI, where, through a virtual embodiment, robot intelligence can interact with an entirely virtual world in a million possible ways, learning from its own mistakes.
We believe that World Models are the foundational technology that can make this possible. These generative models learn from massive amounts of sensor and physical-world data to reach the quality, diversity, and physical realism of the simulated reality that robots require.
I could not be more excited to take on this challenge and build this transformative technology alongside an extraordinary team of engineers and researchers who have spent years working on some of the hardest problems across simulation, generative AI, 3D, robotics, and embodied intelligence.
Together with our investors at @khoslaventures and @radicalvcfund , we intend to push the frontier of this technology and build the foundational infrastructure for interactive robotics learning and evaluation at scale.
Come build this future with us.
And to roboticists, help us understand what you need, we’re building this for you.
veeda.ai
Excited to announce: In 2027 I'll join the UW Allen School (@UWCSE) in Seattle as tenure-track faculty in Computer Science!
My group will advance core geometry processing + 3D AI for visual computing, science, & engineering. I'll be recruiting PhD students in the next cycle!
I innately distrust parameters which aren't powers of 2 or 10.
δ=0.65? lr=0.003? Come on, there's clearly some shenanigans at play here.
Tomorrow I'll speak at the FPTalks series on floating point and numerical analysis, about robust geometry for neural implicit surfaces (work w/ @_AlecJacobson).
The other talks sound amazing, and I love this area! Check out this great organization.
fptalks.org/talks/fptalks26.…
Have you dug deep into an evolving area of visual computing? Consider submitting to the 2027 EG STARs track!
STARs are survey reports providing insight into the current state of the art and future directions. They're impactful and highly-cited!
eg2027.isti.cnr.it/call-for-…
🎉 Excited to introduce TRON, a relighting framework for 3D captures.
💡TRON pairs a neural renderer with 3D Gaussian reconstructions, achieving realistic quality, with 3D, material, & lighting control at interactive frame rates.
arxiv.org/abs/2606.11314
research.nvidia.com/labs/sil…
Nick Sharp retweeted
Releasing Walk on Spheres Extensions (WoSX): a GPU-accelerated C++/Python library for Monte Carlo physics simulation on complex geometry
Think path tracing but for physics beyond light transport: heat, electrostatics, potential flow, deformation & more!
github.com/nv-tlabs/wosx
Nick Sharp retweeted
Paper announcement📢 GimmBO: Interactive Generative Image Model Merging via Bayesian Optimization
Chenxi Liu, Selena Ling (@seleniumlzh), Alec Jacobson
🏆 SIGGRAPH 2026 Best Paper
Selena and I will be presenting in LA (July 19-23)!
🌐 Project: gimmbo-project.github.io/
[1/7]
Nick Sharp retweeted
Code is out! Feel free to try it here: github.com/nv-tlabs/learning…
We’ll also be presenting our work as a CVPR oral at Bluebird Ballroom on Sunday, June 7, at 3:00 PM. Hope to see you there!"
Excited to share our new work at CVPR 2026: Learning Convex Decomposition via Feature Fields.
We introduce the first feedforward openworld model that generates high-quality convex decomposition for any 3D shapes in seconds, enabling faster simulation.
🔗research.nvidia.com/labs/sil…
Visual reconstruction started with meshes, then NeRFs, and now Gaussian Splats.
We went through the same with physical reduced order models: from classic tet meshes, to neural fields, and ultimately a careful particle-based method that gets the best of all worlds. Check it out!
Excited to share FreeForm☁️: Reduced-Order Deformable Simulation from Particle-Based Skinning Eigenmodes at #CVPR2026
FreeForm enables fast elastodynamic simulation for robotics and beyond, directly on messy data (no mesh needed)!
This summer I'll be speaking at LOGML, a program on geometry & learning in London! Come find out how the discrete structure of 3D data meets the tools and techniques of ML 🚀
Applications to the program are still open for a few more days, check it out!
📣 Participant Applications Open: LOGML’26, Imperial College London (13–17 July)
A week on geometry/topology + ML talks, tutorials, projects & networking.
👩🎓 Students/PhD/Postdocs
💰 Limited fee waivers & travel support
🗓 Deadline: 1 May 2026
🔗 Apply: forms.gle/RjxJHCdKVJF41Vvv7
Nick Sharp retweeted
Seeing how realistic video generation has become, I always imagined a model that continuously constructs a 3D world as you move through previously unseen environments. Today, I’m excited that we’ve made it real!
Lyra 2 turns images into explorable 3D worlds—and the environment generated along your trajectory can be exported as 3D Gaussian Splatting and meshes, making it directly usable for real-time rendering and physics simulations.
We scaled up Lyra to generate explorable 3D worlds! 🚀
Introducing Lyra 2.0 — turning a single image into a 3D world you can walk through, look back, and even drop a robot into 🤖
Code and Model available today!
🌐 Website: research.nvidia.com/labs/sil…
(1/N)
Nick Sharp retweeted
We scaled up Lyra to generate explorable 3D worlds! 🚀
Introducing Lyra 2.0 — turning a single image into a 3D world you can walk through, look back, and even drop a robot into 🤖
Code and Model available today!
🌐 Website: research.nvidia.com/labs/sil…
(1/N)
Check out our Lyra2.0 for generating virtual worlds!
The key is combining representations---the generative prior is a video model, but we leverage explicit 3D to scale to large scenes and support physical interaction.
Huge kudos to @TianchangS and @xuanchi13 who led the effort.
Today, we released Lyra 2.0, a framework for generating persistent, explorable 3D worlds at scale, from NVIDIA Research.
Generating large-scale, complex environments is difficult for AI models. Current models often “forget” what spaces look like and lose track of movement over time, causing objects to shift, blur, or appear inconsistent. This prevents them from creating the reliable 3D environments required for downstream simulations. Lyra 2.0 solves these issues by:
✅ Maintaining per-frame 3D geometry to retrieve past frames and establish spatial correspondences
✅ Using self-augmented training to correct its own temporal drifting.
Lyra 2.0 turns an image into a 3D world you can walk through, look back, and drop a robot into for real-time rendering, simulation, and immersive applications.
➡️ Learn more: research.nvidia.com/labs/sil…
📄 Read the paper: arxiv.org/abs/2604.13036
more cool unsupervised shape learning!
HiT: Hierarchical Transformers for Unsupervised 3D Shape Abstraction
- Project: aditya-vora.github.io/HiT/
- Paper: arxiv.org/abs/2510.27088
- Code: github.com/aditya-vora/HiT
We will present HiT at @3DVconf Poster 5-27.
Join us if you are around!
Computing a convex decomposition of a shape is a classically-hard geometry problem, yet essential for fast physics simulators.
Yuezhi found a way to accelerate it by training a large model!
Excited to share our new work at CVPR 2026: Learning Convex Decomposition via Feature Fields.
We introduce the first feedforward openworld model that generates high-quality convex decomposition for any 3D shapes in seconds, enabling faster simulation.
🔗research.nvidia.com/labs/sil…
Totally agree.
Spatial learning needs to be built with a base of tech that is scalable, efficient, precise, and controllable. 3D representations are exactly that.
The best coding models are the ones that use tools the best. Care to guess what will distinguish the best 3D AI?
We don't expect LLMs to multiply numbers or sort lists directly within their output token stream. Instead, we ask them emit code and execute it in a separate runtime.
Why predict the opposite outcome for simulating interactive worlds?
worldlabs.ai/blog/3d-as-code
Great read if you work in 3D.
We're firmly in the middle of the "3D AI era"---why was this change so fast for text & pixels, but still so tricky for 3D? Representations are harder, and data doesn't exist.
Yet in fields beyond vision, 3D is much more than means-to-an-end! (1/2)
In my recent blog post, I argue that "vision" is only well-defined as part of perception-action loops, and that the conventional view of computer vision - mapping imagery to intermediate representations (3D, flow, segmentation...) is about to go away.
vincentsitzmann.com/blog/bit…
























