Rohan Sawhney
@rohansawhney1High-fidelity physics @NVIDIA. @GeomCollective @SCSatCMU alum. @rohansawhney.bsky.social
Similar User
@nmwsharp
@amirvaxman_dgp
@wenzeljakob
@boubek
@HTDerekLiu
@rtwiersma
@JustinMSolomon
@sellan_s
@b_nicolet
@DerekRenderling
@JulieDigne
@nicolefeng_
@Xelatihy
@HonglinChen_
@sinabiz_
The talk, slides, and code for our SGP graduate school course on MCGP can be found here: rohan-sawhney.github.io/mcgp-resources/ We cover a lot of ground: Monte Carlo integration, differential equations, Brownian motion, and of course walk on spheres, which nicely ties all these topics…
And finally @rohansawhney1 and Bailey Miller wrap up the 2024 SGP Graduate School by introducing Monte Carlo Geometry Processing! 🎉
We often think of an "equilibrium" as something standing still, like a scale in perfect balance. But many equilibria are dynamic, like a flowing river which is never changing—yet never standing still. These dynamic equilibria are nicely described by so-called "detailed balance"
There has been significant recent interest in methods that use random walks to solve PDEs. In a project to be presented at SIGGRAPH Asia (w/Ekrem Yılmazer and @DelioVicini), we investigated how to solve *inverse PDE* problems by differentiating such solvers.
The NVIDIA HiFi Physics team is looking for interns with interest/skills in 1⃣ Physics simulation (solids/fluids/differentiable etc) 2⃣ Digital Humans 3⃣ Neural Rendering/Geometry, Video Models 4⃣ Monte Carlo Methods 5⃣ Digital Fabrication Apply: nvidia.wd5.myworkdayjobs.com/en-US/NVIDIAEx…
Our new paper in @NatMachIntell tells a story about how, and why, ML methods for solving PDEs do not work as well as advertised. We find that two reproducibility issues are widespread. As a result, we conclude that ML-for-PDE solving has reached overly optimistic conclusions.
Signed distance functions (SDFs) are fundamental tools in graphics, vision, and physics simulation. But how do you get a high-quality SDF from messy, real-world input? At #SIGGRAPH2024, we introduced a simple method for turning "broken" geometry into a well-behaved SDF. <🧵>
🔍Need efficient distance queries for 2D/3D meshes? Check out FCPW – a user-friendly library in C++ and Python with GPU support! 💻 Get started here: github.com/rohan-sawhney/… Also available on PyPI: pip install fcpw🐍
Signed distance functions (SDFs) are an important surface representation, which can be directly visualized via the “sphere tracing” algorithm. At #SIGGRAPH2024 we showed how to sphere trace a whole new class of surfaces, based on *harmonic functions* rather than SDFs. [1/n]
Attention researchers who want some data to use! blog.activision.com/activision/202…
#SIGGRAPH2024 Neural network and Monte Carlo are two ways to solve your PDEs without any mesh or grid. @jn_pranav combines them to push the boundary of grid-free simulations. We hope this will inspire more work combining these two approaches! See more: pranav-jain.github.io/projects/nmcfs/
Google DeepMind have produced a program that in a certain sense has achieved a silver-medal peformance at this year's International Mathematical Olympiad. 🧵 deepmind.google/discover/blog/…
Need to solve PDEs, and struggle with meshing? Heard about "Walk on Spheres," but didn't know where to start? Check out the awesome intro course by @rohansawhney1 and @baileymmiller1, just posted from #SGP2024: youtube.com/watch?v=1u-5b4…
👀 #SIGGRAPH2024 preview ➡️ nvda.ws/3Llwlyh ✨ #NVIDIAResearch will showcase advancements in #generativeAI and #simulation, showing how simulation research enhances AI models and how #AI models are advancing simulation technology.
Very proud of my group @GeomCollective, for their consistent focus on quality in research. We have 5 papers at #SIGGRAPH2024, including two Best Paper Awards and one Honorable Mention. Only 5 and 12 such awards (respectively) are given out total, from a pool of ~840 submissions
I am excited to finally share our recent paper "Filtering After Shading With Stochastic Texture Filtering" (with Matt Pharr, @marcosalvi, and Marcos Fajardo), published at ACM I3D'24 / PACM CGIT, where we won the best paper award! 1/N
United States Trends
- 1. Cowboys 67,9 B posts
- 2. Clippers 9.831 posts
- 3. Texans 55,1 B posts
- 4. Norman Powell 1.712 posts
- 5. Cooper Rush 11,7 B posts
- 6. Jerry 42,4 B posts
- 7. Mike McCarthy 3.128 posts
- 8. Joe Mixon 10,2 B posts
- 9. Trey Lance 3.105 posts
- 10. Lindy 3.364 posts
- 11. Dyson Daniels 2.558 posts
- 12. Keon Ellis 1.598 posts
- 13. #WWERaw 61,1 B posts
- 14. Harden 18,4 B posts
- 15. sabrina 104 B posts
- 16. #HOUvsDAL 9.460 posts
- 17. The Herta 19,6 B posts
- 18. Sixers 10,9 B posts
- 19. Pulisic 24,2 B posts
- 20. #TheFutureIsTeal N/A
Who to follow
-
Nick Sharp
@nmwsharp -
Amir Vaxman
@amirvaxman_dgp -
Wenzel Jakob {deprecation notice}
@wenzeljakob -
Tamy Boubekeur
@boubek -
Hsueh-Ti Derek Liu
@HTDerekLiu -
Ruben Wiersma
@rtwiersma -
Justin Solomon
@JustinMSolomon -
Silvia Sellán
@sellan_s -
Baptiste Nicolet
@b_nicolet -
Derek Nowrouzezahrai
@DerekRenderling -
Julie Digne
@JulieDigne -
Nicole Feng
@nicolefeng_ -
Fabio Pellacini
@Xelatihy -
Honglin Chen
@HonglinChen_ -
sina nabizadeh / سینا
@sinabiz_
Something went wrong.
Something went wrong.