Selena Ling's Avatar

Selena Ling

@selenaling.bsky.social

https://iszihan.github.io/

65 Followers  |  32 Following  |  10 Posts  |  Joined: 26.04.2023  |  1.6927

Latest posts by selenaling.bsky.social on Bluesky

Post image

At SIGGRAPH 2025, we’ll be presenting the paper β€œStochastic Barnes-Hut Approximation for Fast Summation on the GPU”. By injecting a bit of randomization into the classic yet deterministic Barnes-Hut approximation for fast kernel summation, we can achieve nearly 10x speedups on the GPU!

05.06.2025 21:44 β€” πŸ‘ 42    πŸ” 9    πŸ’¬ 1    πŸ“Œ 3

We show many more experiments across different implicit surface representations in our paper. Please check out our #SGP25 paper here arxiv.org/pdf/2506.05268 and reach out if you have any questions! Code coming soon! (9/9)

10.06.2025 14:40 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Post image

With uniformly sampled points, one can also easily perform importance sampling using curvature or other quantities like losses, and construct geometry-aware regularization terms to improve neural implicit optimization. (8/9)

10.06.2025 14:40 β€” πŸ‘ 3    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Post image

Our white noise samples are also essential for enabling neural implicit deformation as proposed in [Yang et al. 2021]. (7/9)

10.06.2025 14:40 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Post image

A uniformly sampled set of points on implicit surfaces enables many downstream applications:

One can take our white noise samples and easily subsample to blue noise samples. (6/9)

10.06.2025 14:40 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Post image

More specifically, sampling on extracted meshes from isosurfacing algorithms like Marching Cubes requires expensive evaluation to a grid and easily aliases thin structures, while our method is both efficient and accurate. (5/9)

10.06.2025 14:40 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Post image

Our method is more efficient than the common alternatives: rejection sampling, sampling on extracted meshes via Marching Cubes, and a principled sampling algorithm using Markov chain Monte Carlo (e.g., Hamiltonian Monte Carlo). (4/9)

10.06.2025 14:40 β€” πŸ‘ 3    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Video thumbnail

Our method exploits a classic mathematical relationship: to sample a point set, gather all intersections of randomly-cast rays against the surface β€” and intersecting rays with implicit surfaces is easy! (3/9)

10.06.2025 14:40 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

Suppose you have an implicit surface, like a neural SDF or shadertoy-style analytic function, and you want to uniformly sample points on the surface π˜„π—Άπ˜π—΅π—Όπ˜‚π˜ lossy mesh extraction. (2/9)

10.06.2025 14:40 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Video thumbnail

Our #SGP25 work studies a simple and effective way to uniformly sample implicit surfaces by casting rays. (1/9)

β€œUniform Sampling of Surfaces by Casting Rays” w/ @abhishekmadan.bsky.social @nmwsharp.bsky.social and Alec Jacobson

10.06.2025 14:40 β€” πŸ‘ 48    πŸ” 17    πŸ’¬ 1    πŸ“Œ 2
Post image

According to the SIGGRAPH Executive Committee Meeting Minutes, SIGGRAPH Asia 2026 will take place in Malasyia, the *second most deadly country for trans people in the entire world*

26.02.2025 21:23 β€” πŸ‘ 21    πŸ” 6    πŸ’¬ 5    πŸ“Œ 1

Check out our latest #Siggraph25 work!

03.06.2025 01:16 β€” πŸ‘ 6    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

@selenaling is following 19 prominent accounts