Power Foam unifies real-time differentiable ray tracing and rasterization by replacing unbounded Voronoi cells with controllable bounded power diagrams, oriented surfaces, and embedded textures.
arXiv preprint arXiv:2512.14180 (2025) 2, 10, 11
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
SAD is a new explicit differentiable image representation based on soft anisotropic additively weighted Voronoi partitions that achieves higher PSNR and 4-19x faster training than Image-GS and Instant-NGP at matched bitrate.
A learnable confidence framework in 3D Gaussian Splatting balances photometric and geometric losses while penalizing per-primitive variance to produce state-of-the-art unbounded meshes efficiently.
Neural Harmonic Textures add periodic feature interpolation and deferred neural decoding to primitive representations, achieving state-of-the-art real-time novel-view synthesis and bridging primitive and neural-field methods.
citing papers explorer
-
Power Foam: Unifying Real-Time Differentiable Ray Tracing and Rasterization
Power Foam unifies real-time differentiable ray tracing and rasterization by replacing unbounded Voronoi cells with controllable bounded power diagrams, oriented surfaces, and embedded textures.
-
Soft Anisotropic Diagrams for Differentiable Image Representation
SAD is a new explicit differentiable image representation based on soft anisotropic additively weighted Voronoi partitions that achieves higher PSNR and 4-19x faster training than Image-GS and Instant-NGP at matched bitrate.
-
Confidence-Based Mesh Extraction from 3D Gaussians
A learnable confidence framework in 3D Gaussian Splatting balances photometric and geometric losses while penalizing per-primitive variance to produce state-of-the-art unbounded meshes efficiently.
-
Neural Harmonic Textures for High-Quality Primitive Based Neural Reconstruction
Neural Harmonic Textures add periodic feature interpolation and deferred neural decoding to primitive representations, achieving state-of-the-art real-time novel-view synthesis and bridging primitive and neural-field methods.