AWhat changed
Paired trainable multiresolution hash-grid features with small neural networks and fused GPU kernels to accelerate fitting and rendering of neural graphics primitives.
Scientific scope
Paired trainable multiresolution hash-grid features with small neural networks and fused GPU kernels to accelerate fitting and rendering of neural graphics primitives. NeRF, grid encodings and hashing have predecessors; acquire this representation/implementation combination, not invention of neural radiance fields. Collisions, feature-memory cost and scene/device-dependent quality-speed tradeoffs remain.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. NeRF, grid encodings and hashing have predecessors; acquire this representation/implementation combination, not invention of neural radiance fields. Collisions, feature-memory cost and scene/device-dependent quality-speed tradeoffs remain.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
- Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
- Müller et al.: multiresolution hash encoding for neural graphics — author/institutional project
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction