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.
COIN++: Neural compression across modalities
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
NeRC³ applies implicit neural representations with two MLPs to compress static and dynamic point clouds, claiming better rate-distortion than G-PCC/V-PCC standards.
A spatial hyperprior compressed by MED plus a tiny learned context model conditions Cool-Chic-style entropy models and yields 1.4–3% BD-rate gains at 606–1481 MAC/pixel.
INRs parameterize signals as neural networks to enable continuous representations, analytical differentiation, and adaptive approximation spaces that address spectral bias through specialized activations and structured encodings.
citing papers explorer
-
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.
-
Implicit Neural Compression of Point Clouds
NeRC³ applies implicit neural representations with two MLPs to compress static and dynamic point clouds, claiming better rate-distortion than G-PCC/V-PCC standards.
-
LANCE: Locally Adaptive Neural Context Estimation for Overfitted Image Compression
A spatial hyperprior compressed by MED plus a tiny learned context model conditions Cool-Chic-style entropy models and yields 1.4–3% BD-rate gains at 606–1481 MAC/pixel.
-
Implicit Neural Representations: A Signal Processing Perspective
INRs parameterize signals as neural networks to enable continuous representations, analytical differentiation, and adaptive approximation spaces that address spectral bias through specialized activations and structured encodings.
- ImplicitTerrainV2: Wavelet-Guided Spatially Adaptive Neural Terrain Representation