iiinova — where your digital self keeps evolving

Nicholas Sharp @nmwsharp.bsky.social · 02/09/2026

Just watched a coding agent waste an entire afternoon of experiments because it got the sign convention for the Laplacian backward 😅 This is a convincing geometry processing Turing test --- it's indistinguishable from a human geometer!

080

Nicholas Sharp @nmwsharp.bsky.social · 18/08/2026

Excited to announce: In 2027 I'll join the UW Allen School 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!

3411

Nicholas Sharp @nmwsharp.bsky.social · 13/08/2026

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.

080

Nicholas Sharp @nmwsharp.bsky.social · 05/08/2026

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/fptalk...

0132

Nicholas Sharp @nmwsharp.bsky.social · 30/07/2026

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-sta...

084

Reposted by Nicholas Sharp

Ahmed Mahmoud @ahdhn.bsky.social · 14/07/2026

Next week at #SIGGRAPH 2026, we'll present "Locality-Aware Automatic Differentiation on the GPU for Mesh-Based Computations," with Rahul Goel, Jonathan Ragan-Kelley, and @justinmsolomon.bsky.social . Talk: Mon., July 20, 2:50 PM, Room 403-B Paper: dl.acm.org/doi/10.1145/... More below (1/7):

22111

Reposted by Nicholas Sharp

LOGML Summer School @logml.bsky.social · 15/05/2026

📣 LOGML'26 Speaker Series 🎤 Nicholas Sharp @nmwsharp.bsky.social (NVIDIA) Researcher in geometry processing, computer graphics/vision & 3D ML — building methods for geometric computing. 📍 Imperial College London 📅 13–17 July 2026 Website: 🔗 www.logml.ai/ #LOGML #Summerschool #MachineLearning

022

Nicholas Sharp @nmwsharp.bsky.social · 15/04/2026

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 Tianchang+Xuanchi who led it. research.nvidia.com/labs/sil/pro...

0101

Reposted by Nicholas Sharp

WiGRAPH @wigraph.bsky.social · 11/03/2026

Our Rising Stars 2026 application campaign is currently open so we thought we would share some updates about our past rising stars 🌟 follow us in the next couple weeks to read more! Learn more about the program and apply >> www.wigraph.org/events/2026-...

wigraph.org

Call for Rising Stars Applications

The Rising Stars in Computer Graphics program is designed to bring new perspectives to computer graphics research. This is a two-year program that will be co-located with SIGGRAPH 2026 and SIGGRAPH 20...

122

Nicholas Sharp @nmwsharp.bsky.social · 11/03/2026

My understanding is that in eg. the physics simulation context the approximation setting is pretty universal, because even the best exact convex decomp of a complicated shape is impractically complex for fast simulation. (Though certainly the exact case is important and interesting mathematically!)

110

Nicholas Sharp @nmwsharp.bsky.social · 11/03/2026

Thanks! I suspect your understanding is correct, hopefully the text of the paper makes the sense in which this is approximate clear. Two equivalent viewpoints: - We emit a union of convex bodies, approximating the shape - We split the shape into pieces, each of which is approximately convex

110

Nicholas Sharp @nmwsharp.bsky.social · 11/03/2026

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!

181

Reposted by Nicholas Sharp

David Levin @diwlevin.bsky.social · 29/01/2026

My PhD student Abhishek Madan is getting ready to graduate and he’s looking for a postdoc or industry position. Checkout his website www.dgp.toronto.edu/~amadan/ He’s been an amazing student , basically does all his research by himself. Fantastic math and implementation acumen.

dgp.toronto.edu

Abhishek Madan

075

Reposted by Nicholas Sharp

rishit dagli @rishit-dagli.bsky.social · 30/10/2025

📢want to create realistic dynamic 3D worlds (>100 splats)? my NVIDIA internship project, VoMP, is the first feed-forward approach turning surface geometry into volumetric sim-ready assets with real-world materials. 🌐Project: research.nvidia.com/labs/sil/pro... 📜Paper: arxiv.org/abs/2510.22975

4465

Nicholas Sharp @nmwsharp.bsky.social · 15/10/2025

The Spatial Intelligence Lab at NVIDIA (research.nvidia.com/labs/sil/) is looking for 2026 research interns! We do all kinds of cool work across graphics/vision, geometry, physics, & ML. Now is the time to apply & reach out! nvidia.eightfold.ai/careers/job/... (not limited to Canada-only)

research.nvidia.com

NVIDIA Spatial Intelligence Lab (SIL)

Advancing foundational technologies enabling AI systems to perceive, model, and interact with the physical world.

060

Nicholas Sharp @nmwsharp.bsky.social · 04/07/2025

Also: this paper was recognized with a best paper award at SGP! Huge thanks to the organizers & congrats to the other awardees. I was super lucky to work with Yousuf on this one, he's truly the mastermind behind it all!

0130

Nicholas Sharp @nmwsharp.bsky.social · 02/07/2025

Actually, Yousuf did a quick experiment which is related (though a different formulation), using @markgillespie64.bsky.social et al's Discrete Torsion Connection markjgillespie.com/Research/Dis.... You get fun spiraling log maps! (image attached)

010

Nicholas Sharp @nmwsharp.bsky.social · 02/07/2025

Yeah! That diffused frame is "the most regular frame field in the sense of transport along geodesics from the source", so you get out a log map that is as-regular-as-possible, in the same sense. You could definitely use another frame field, and you'd get "log maps" warped along that field.

110

Nicholas Sharp @nmwsharp.bsky.social · 02/07/2025

💻 Website: www.yousufsoliman.com/projects/the... 📗 Paper: www.yousufsoliman.com/projects/dow... 🔬 Code (C++ library): geometry-central.net/surface/algo... 🐍 Code (python bindings): github.com/nmwsharp/pot... (point cloud code not available yet, let us know if you're interested!)

091

Nicholas Sharp @nmwsharp.bsky.social · 02/07/2025

We give two variants of the algorithm, and show use cases for many problems like averaging values on surfaces, decaling, and stroke-aligned parameterization. It even works on point clouds!

180

Nicholas Sharp @nmwsharp.bsky.social · 02/07/2025

Instead of the usual VxV scalar Laplacian, or a 2Vx2V vector Laplacian, we build a 3Vx3V homogenous "affine" Laplacian! This Laplacian allows new algorithms for simpler and more accurate computation of the logarithmic map, since it captures rotation and translation at once.

160

Nicholas Sharp @nmwsharp.bsky.social · 02/07/2025

Previously in "The Vector Heat Method", we computed log maps with short-time heat flow, via a vector-valued Laplace matrix rotating between adjacent vertex tangent spaces. The big new idea is to rotate **and translate** vectors, by working homogenous coordinates.

160

Nicholas Sharp @nmwsharp.bsky.social · 02/07/2025

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

26815

Reposted by Nicholas Sharp

David Levin @diwlevin.bsky.social · 18/06/2025

Holding SIGGRAPH Asia 2026 in Malaysia is a slap in the face to the rights of LGBTQ+ people. Especially now, when underrepresented people need as much support as we can possibly give them ! Angry like me ? Sign this open letter to let them know. 🏳️‍⚧️🏳️‍🌈 docs.google.com/document/d/1...

docs.google.com

Open Letter to the SIGGRAPH Leadership

RE: Call for SIGGRAPH Asia to relocate from Malaysia and commit to a venue selection process that safeguards LGBTQ+ and other at-risk communities. To the SIGGRAPH Leadership: SIGGRAPH Executive Commit...

13014

Nicholas Sharp @nmwsharp.bsky.social · 10/06/2025

Sampling points on an implicit surface is surprisingly tricky, but we know how to cast rays against implicit surfaces! There's a classic relationship between line-intersections and surface-sampling, which turns out to be quite useful for geometry processing.

1191

Nicholas Sharp @nmwsharp.bsky.social · 08/06/2025

Thank you! There's definitely a low-frequency bias when stochastic preconditioning is enabled, but we only use it for the first ~half of training, then train as-usual. The hypothesis is that the bias in the 1st half helps escape bad minima, then we fit high-freqs in the 2nd half. Coarse to fine!

000

Reposted by Nicholas Sharp

Masha Sh. @shumash.bsky.social · 06/06/2025

My child’s doll and tools I captured as 3D Gaussians, turned digital with collisions and dynamics. We are getting closer to bridging the gap between the world we can touch and digital 3D. Experience the bleeding edge at #NVIDIA Kaolin hands-on lab, #CVPR2025! Wed, 8-noon. tinyurl.com/nv-kaolin-cv...

3102

Nicholas Sharp @nmwsharp.bsky.social · 05/06/2025

Check out Abhishek's research! I was honestly surprised by this result: classic Barnes-Hut already builds a good spatial hierarchy for approximating kernel summations, but you can do even better by adding some stochastic sampling, for significant speedups on the GPU @ matching average error.

0140

Nicholas Sharp @nmwsharp.bsky.social · 04/06/2025

Ah yes absolutely. That's a great example, we totally should have cited it! When we looked around we found mannnnnny various "coarse-to-fine" like schemes appearing in the context of particular problems or architectures. As you say, what most excited us here is having simple+general option.

100

Nicholas Sharp @nmwsharp.bsky.social · 04/06/2025

Thank you for the kind words :) The technique is very much in-the-vein of lots of related ideas in ML, graphics, and elsewhere, but hopefully directly studying it & sharing is useful to the community!

010

Nicholas Sharp @nmwsharp.bsky.social · 04/06/2025

We did not try it w/ the Gaussians in this project (we really focused on the "query an Eulerian field" setting, which is not quite how Gaussian rendering works). There are some very cool projects doing related things in that setting: - ubc-vision.github.io/3dgs-mcmc/ - diglib.eg.org/items/b8ace7...

010

Nicholas Sharp @nmwsharp.bsky.social · 03/06/2025

Tagging @selenaling.bsky.social and @merlin.ninja, who are both on here it turns out! 😁

110

Nicholas Sharp @nmwsharp.bsky.social · 03/06/2025

website: research.nvidia.com/labs/toronto... arxiv: arxiv.org/abs/2505.20473 code: github.com/iszihan/stoc... Kudos go to Selena Ling who is the lead author of this work, during her internship with us at NVIDIA. Reach out to Selena or myself if you have any questions!

research.nvidia.com

Stochastic Preconditioning for Neural Field Optimization

120

Nicholas Sharp @nmwsharp.bsky.social · 03/06/2025

Closing thought: In geometry, half our algorithms are "just" Laplacians/smoothness/heat flow under the hood. In ML, half our techniques are "just" adding noise in the right place. Unsurprisingly, these two tools work great together in this project. I think there's a lot more to do in this vein!

240

Nicholas Sharp @nmwsharp.bsky.social · 03/06/2025

Geometric initialization is a commonly-used technique to accelerate SDF field fitting, yet it often results in disastrous artifacts for non-object centric scenes. Stochastic preconditioning also helps to avoid floaters both with and without geometric initialization.

100

Nicholas Sharp @nmwsharp.bsky.social · 03/06/2025

Neural field training can be sensitive to changes to hyperparameters. Stochastic preconditioning makes training more robust to hyperparameter choices, shown here in a histogram of PSNRs from fitting preconditioned and non-preconditioned fields across a range of hyperparameters.

100

Nicholas Sharp @nmwsharp.bsky.social · 03/06/2025

We argue that this is a quick and easy form of coarse-to-fine optimization, applicable to nearly any objective or field representation. It matches or outperforms custom designed polices and staged coarse-to-fine schemes.

120

Nicholas Sharp @nmwsharp.bsky.social · 03/06/2025

Surprisingly, optimizing this blurred field to fit the objective greatly improves convergence, and in the end we anneal 𝛼 to 0 and are left with an ordinary un-blurred field.

100

Nicholas Sharp @nmwsharp.bsky.social · 03/06/2025

And implementing our method requires changing just a few lines of code!

100

Nicholas Sharp @nmwsharp.bsky.social · 03/06/2025

It’s as simple as perturbing query locations according to a normal distribution. This produces a stochastic estimate of the blurred neural field, with the level of blur proportional to a scale parameter 𝛼.

120

Nicholas Sharp @nmwsharp.bsky.social · 03/06/2025

Selena's #Siggraph25 work found a simple, nearly one-line change that greatly eases neural field optimization for a wide variety of existing representations. “Stochastic Preconditioning for Neural Field Optimization” by Selena Ling, Merlin Nimier-David, Alec Jacobson, & me.

3538

Reposted by Nicholas Sharp

Keenan Crane @keenancrane.bsky.social · 21/05/2025

Fun new paper at #SIGGRAPH2025: What if instead of two 6-sided dice, you could roll a single "funky-shaped" die that gives the same statistics (e.g, 7 is twice as likely as 4 or 10). Or make fair dice in any shape—e.g., dragons rather than cubes? That's exactly what we do! 1/n

814946

Nicholas Sharp @nmwsharp.bsky.social · 01/04/2025

The Symposium on Geometry Processing is an amazing venue for geometry research: meshes, point clouds, neural fields, 3D ML, etc. Reviews are quick and high-quality. The deadline is in ~10 days. Consider submitting your work, I'm planning to submit! sgp2025.my.canva.site/submit-page-...

sgp2025.my.canva.site

SGP 2025 - Submit page

04210

Nicholas Sharp @nmwsharp.bsky.social · 19/03/2025

Hi BlueSky! I'm trying to get back to a "write" relationship with social media after hiding from it for a while. I like geometry research, useful code, pierogies [sic], triangles, outdoorsy life, etc. I mainly post about research/software, but glad to chat about anything.

5491