Selena Ling
@selenaling.bsky.social
66 followers 32 following 10 posts
https://iszihan.github.io/
Posts Media Videos Starter Packs
Reposted by Selena Ling
abhishekmadan.bsky.social
At SIGGRAPH 2025, we’ll be presenting the paper “Stochastic 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!
selenaling.bsky.social
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)
arxiv.org
selenaling.bsky.social
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)
selenaling.bsky.social
Our white noise samples are also essential for enabling neural implicit deformation as proposed in [Yang et al. 2021]. (7/9)
selenaling.bsky.social
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)
selenaling.bsky.social
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)
selenaling.bsky.social
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)
selenaling.bsky.social
Our method exploits a classic mathematical relationship: to sample a point set, gather all intersections of randomly-cast rays against the surface — and intersecting rays with implicit surfaces is easy! (3/9)
selenaling.bsky.social
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 𝘄𝗶𝘁𝗵𝗼𝘂𝘁 lossy mesh extraction. (2/9)
selenaling.bsky.social
Our #SGP25 work studies a simple and effective way to uniformly sample implicit surfaces by casting rays. (1/9)

“Uniform Sampling of Surfaces by Casting Rays” w/ @abhishekmadan.bsky.social @nmwsharp.bsky.social and Alec Jacobson
Reposted by Selena Ling
silviasellan.bsky.social
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*
selenaling.bsky.social
Check out our latest #Siggraph25 work!
nmwsharp.bsky.social
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.