Nick Sharp @nmwsharp

3D geometry researcher: graphics, vision, 3D ML, etc | Senior Research Scientist @NVIDIA | running, hockey, baking, & cheesy sci fi | opinions my own | he/him nmwsharp.com Seattle, WA Joined May 2018

Tweets

617
Followers

6K
Following

323
Likes

2K

Nick Sharp @nmwsharp

2 weeks ago

@Colonthreee @yousufmsoliman It's very related! It's the latest in a line of advanced algorithms for decaling. See also things like @rms80's expmaps dgp.toronto.edu/~rms/software/… Compared to classic approaches, these geometric methods can wrap decals around curved meshes, and aren't affected by UV seams.

0 0 3 65 0

View Details

Nick Sharp @nmwsharp

12 months ago

Logarithmic maps are incredibly useful for algorithms on surfaces--they're local 2D coordinates centered at a given source. @yousufmsoliman and I found a better way to compute log maps w/ fast short-time heat flow in "The Affine Heat Method" presented @ SGP2025 today! 🧵

3 76 483 37K 242

View Details

Rohan Sawhney @rohansawhney1

2 weeks ago

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

7 65 524 117K 358

View Details

Chenxi Liu @chenxil21

2 weeks ago

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]

2 8 44 4K 12

View Details

Yuezhi Yang @yang_yuezhi

3 weeks ago

Code is out! Feel free to try it here: github.com/nv-tlabs/learn… 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!"

Yuezhi Yang @yang_yuezhi

3 months ago

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/proje…

4 34 204 40K 112

0 8 35 6K 7

View Details

Nick Sharp @nmwsharp

3 weeks ago

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!

Donglai Xiang @DonglaiXiang

3 weeks ago

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)!

1 14 69 11K 31

0 3 25 3K 9

View Details

Nick Sharp @nmwsharp

a month ago

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!

LOGML Summer School @LogmlSchool

2 months ago

📣 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/RjxJHCdKVJF41V…

1 17 63 11K 47

2 2 20 3K 2

View Details

Tianchang Shen @TianchangS

2 months ago

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.

Xuanchi Ren @xuanchi13

2 months ago

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/proje… (1/N)

29 121 873 1.1M 379

4 8 65 7K 21

View Details

Xuanchi Ren @xuanchi13

2 months ago

29 121 873 1.1M 379

View Details

Nick Sharp @nmwsharp

2 months ago

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.

NVIDIA AI Developer @NVIDIAAIDev

2 months ago

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

100 461 3K 434K 2K

2 3 48 5K 11

View Details

Nick Sharp @nmwsharp

3 months ago

@lily_goli @yang_yuezhi this is awesome, we should all chat sometime!

1 0 5 95 0

View Details

Nick Sharp @nmwsharp

3 months ago

more cool unsupervised shape learning!

Aditya Vora @anvorain

3 months ago

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!

2 14 72 17K 43

0 2 27 4K 12

View Details

Nick Sharp @nmwsharp

3 months ago

@toshi2k2 @yang_yuezhi @CVPR Hi Prakhar, your paper looks very cool! To be clear our paper here is specifically focused on the geometric task of *convex decomposition* rather than semantic 3D segmentation; it's almost more of an acceleration structure. Looking forward to chatting more at CVPR!

0 0 0 92 0

View Details

Nick Sharp @nmwsharp

3 months ago

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!

Yuezhi Yang @yang_yuezhi

3 months ago

4 34 204 40K 112

1 13 110 10K 57

View Details

Nick Sharp @nmwsharp

4 months ago

@yongyuanxi Too long for a tweet :) All of the above pretty much! Personally I think most about tasks where we want to analyze or generate the real physical world around us in some way; fabrication is a great one. But this involves a stack of tools from basic data to high-level reasoning.

1 0 7 520 0

View Details

Nick Sharp @nmwsharp

4 months ago

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?

Ben Mildenhall @BenMildenhall

4 months ago

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

21 24 265 57K 142

1 3 42 8K 26

View Details

Nick Sharp @nmwsharp

4 months ago

@MenyJanos "IDEs" here is meant as more of an abbreviated blanket term for "code tooling", and I'd say that's gone into overdrive lately rather than disappearing. For me at least, LLM coding is filled with new interfaces, MCPs, review tools, etc, and my compiler is working harder than ever.

1 0 1 85 0

View Details

Nick Sharp @nmwsharp

4 months ago

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)

Vincent Sitzmann @vincesitzmann

4 months ago

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/bitter_le…

44 163 1K 392K 791

1 3 81 13K 52

View Details

Nick Sharp @nmwsharp

4 months ago

@MattNiessner LLMs both help and hurt in this sense. In some ways they very much help us communicate clearly more efficiently. But also, they make it easy to disguise ill-posed ideas under a veneer of confident polish, which takes significant effort to detect.

0 0 2 338 0

View Details

Nick Sharp @nmwsharp

4 months ago

@MattNiessner I disagree; the most important role of a paper is not any numerical score it achieves, but its ability to coherently communicate a new idea, so the reader can build something even better atop it. Clear presentation is hugely important. Papers are not high-score leaderboards!