REVIEW 9 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
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 9 Pith papers
-
Locality-Aware Density Control for Efficient Gaussian-based Image Representation
A locality-aware density-control framework for 2D Gaussian image representation that densifies coherent high-error regions and merges redundant similar Gaussians, improving PSNR at fixed budgets.
-
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.
-
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.
-
Weight Space Representation Learning via Neural Field Adaptation
Multiplicative LoRA weights of pre-trained neural fields form structured, semantically meaningful representations that outperform prior weight-space methods for generation and classification.
-
Deep Unrolling of Sparsity-Induced RDO for 3D Point Cloud Attribute Coding
An unrolled proximal-gradient network encodes point cloud attributes at O(N) complexity, outperforming MPEG G-PCC RAHT with prediction by 6-11% bit rate.
-
Structure-Preserving Patch Decoding for Efficient Neural Video Representation
Splitting video frames with PixelUnshuffle into structure-preserving patches and decoding them with a global-to-local network improves INR video reconstruction over NeRV-style baselines.
-
Large Images are Gaussians: High-Quality Large Image Representation with Levels of 2D Gaussian Splatting
A two-level 2D Gaussian splatting method with direct covariance optimization fits large images with more Gaussian points and higher PSNR than prior Gaussian-based image representation.
-
SBS: Enhancing Parameter-Efficiency of Neural Representations for Neural Networks via Spectral Bias Suppression
SBS improves NeRN weight compression by unidirectional kernel smoothing and RFF bandwidth that shrinks for larger networks, cutting required MLP parameters by roughly 2 to 3 times.
-
How to Design and Train Your Implicit Neural Representation for Video Compression
Under equal training time, a recombined NeRV architecture (RNeRV) beats prior NeRV variants on UVG, and weight token masking lets hyper-network codecs trade bitrate for quality.
Discussion (0). Continue with ORCID to comment.