AMD researchers propose BVH-based position encoding for neural ray tracing
ssh4net · x · 2026-10-19
AMD researchers Daniel Meister and Takahiro Harada published 'BVH Encoding for Neural-Assisted Ray Tracing,' a novel 3D position encoding for neural networks in ray tracing. The method reuses the bounding volume hierarchy (BVH) — already an acceleration structure — as a spatial index for learnable latent feature vectors: a cut of BVH nodes stores feature vectors at bounding-box corners, fetched via bi-linear interpolation. The encoding adapts naturally to scene geometry, supports general geometric primitives, and keeps memory bounded regardless of scene complexity. They demonstrate it in a neural radiance cache (NRC) application, comparing against hash-grid encoding with FLIP error maps.
More from Research
- Wolfram Opens Rule 30 Prizes to AIs: $30,000 for Three Open Problems — cephaloform · 2026-10-23
- Stanford and Databricks use AI agents to reproduce medical findings and test analytical robustness — ChengleiSi · 2026-10-23
- EMNLP paper: diffusion LMs internally encode latent denoising timestep representations — gsarti_ · 2026-10-23
- KU Leuven and VIB open two Group Leader professorships in AI for Biology, start 2027 — jpillowtime · 2026-10-23
- Subspace Tuning curbs LLM catastrophic forgetting by freezing principal singular directions — scottniekum · 2026-10-23
- Perceptic launches PercepticOS, an AI workspace for 'scientific superintelligence' — nathanbenaich · 2026-10-23