Delaunay-based nearest-neighbor search delivers 57x faster ambient occlusion than Three.js GTAO
ssh4net · x · 2026-11-14
A developer built a real-time ambient occlusion technique based on the new paper "Delaunay-Based Nearest Neighbor Search with Grid-Accelerated Queries and Parallel Construction", reporting 24x speedup over Three.js SSAO and 57x over Three.js GTAO.
Benchmarks on Apple M1 (1280×720, 1.12m radius, median GPU time) show the SDF 4-tap approach at 0.183ms versus 4.507ms for Three.js SSAO and 10.360ms for GTAO, with visually comparable contact shadows and recess detail in a warehouse scene.
More from Research
- Cambridge mRNA therapy regrows heart muscle after attack, boosts pumping 10% in mice — kimmonismus · 2026-11-14
- Data curation RL is just SWE envs: code pretraining data increasingly consists of Claude-built, less-sloppy repos — willcb · 2026-11-14
- NeurIPS 2025 best paper: diffusion models start memorizing at ~300 steps per image — Mastbubbles · 2026-11-14
- TestPrune: pruning regression tests to unblock AI-driven autonomous bug fixing — burkov · 2026-11-14
- Toddlers learn new verbs only from responsive partners; a call to rerun the test with AI — AnnaCiaunica · 2026-11-14
- Context beats model choice: Databricks benchmark shows 91% vs 58% for data agents — CautiousUse8597 · 2026-11-14