REVIEW 13 cited by
COIN: COmpression with Implicit Neural representations
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
COIN: COmpression with Implicit Neural representations
read the original abstract
We propose a new simple approach for image compression: instead of storing the RGB values for each pixel of an image, we store the weights of a neural network overfitted to the image. Specifically, to encode an image, we fit it with an MLP which maps pixel locations to RGB values. We then quantize and store the weights of this MLP as a code for the image. To decode the image, we simply evaluate the MLP at every pixel location. We found that this simple approach outperforms JPEG at low bit-rates, even without entropy coding or learning a distribution over weights. While our framework is not yet competitive with state of the art compression methods, we show that it has various attractive properties which could make it a viable alternative to other neural data compression approaches.
Forward citations
Cited by 13 Pith papers
-
ImplicitTerrainV2: Wavelet-Guided Spatially Adaptive Neural Terrain Representation
A wavelet-guided adaptive INR for DEMs achieves 66.25 dB PSNR on Swiss tiles with 3.2x fewer parameters than prior work, plus post-training compression to 1.23 bpp.
-
What Cohort INRs Encode and Where to Freeze Them
Optimal INR freeze depth matches highest weight stable rank layer; SAEs reveal SIREN atoms are localized while FFMLP atoms trace cohort contours with causal impact on PSNR.
-
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.
-
AIR: Amortized Image Reconstruction Framework for Self-Supervised Feed-Forward 2D Gaussian Splatting
AIR amortizes 2D Gaussian splatting into a self-supervised feed-forward network via residual stages, explicit stage control, and Predict-Optimize-Distill training.
-
LANCE: Locally Adaptive Neural Context Estimation for Overfitted Image Compression
LANCE extends OIC frameworks with a spatial hyperprior and predictive coding scheme, reporting BD-rate gains of 1.4-3% over Cool-Chic 4.0 on Kodak and CLIC.
-
CWRNN-INVR: A Coupled WarpRNN based Implicit Neural Video Representation
CWRNN-INVR combines WarpRNN for structured video information and residual grids for irregular details to reach 33.73 dB average PSNR on the UVG dataset at 3M parameters, outperforming existing INVR methods.
-
GAIR: Location-Aware Self-Supervised Contrastive Pre-Training with Geo-Aligned Implicit Representations
GAIR introduces a geo-aligned implicit representation module inside a multi-encoder contrastive SSL framework that produces location-aware embeddings and outperforms prior geo-foundation models on 22 geospatial datase...
-
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.
-
Ray-driven Spectral CT Reconstruction Based on Neural Base-Material Fields
A ray-driven neural base-material field model parameterizes attenuation coefficients as continuous implicit functions and uses auto-differentiation to solve spectral CT reconstruction.
-
Cool-chic 5.0: Faster Encoding and Inter-Feature Entropy Modeling for Overfitted Image Compression
Cool-chic 5.0 delivers 11% lower rate than H.266/VVC and matches modern autoencoders like MLIC++ with 250 times lower decoding complexity through an updated decoder architecture and faster optimization for overfitted codecs.
-
Location Is All You Need: Continuous Spatiotemporal Neural Representations of Earth Observation Data
LIANet encodes multi-temporal Earth observation data into a coordinate-based neural field that supports label-only fine-tuning for downstream tasks without access to raw imagery.
-
PaaF: Raising the perceived quality of INR-Based Image Compression
PaaF is an INR-based image codec that adds architectural changes, adaptive quantization, and entropy coding to improve quantitative metrics and perceptual quality over existing INR compression methods.
-
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 structure...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.