Pith. sign in

REVIEW 4 cited by

COIN++: Neural Compression Across Modalities

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2201.12904 v3 pith:QS7OSYOG submitted 2022-01-30 cs.LG cs.CVeess.IVstat.ML

Emilien Dupont , Hrushikesh Loya , Milad Alizadeh , Adam Goliński , Yee Whye Teh , Arnaud Doucet This is my paper
classification cs.LGcs.CVeess.IVstat.ML
keywords dataneuralcompressionmodalitiescodecoinimplicitmodulations
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Neural compression algorithms are typically based on autoencoders that require specialized encoder and decoder architectures for different data modalities. In this paper, we propose COIN++, a neural compression framework that seamlessly handles a wide range of data modalities. Our approach is based on converting data to implicit neural representations, i.e. neural functions that map coordinates (such as pixel locations) to features (such as RGB values). Then, instead of storing the weights of the implicit neural representation directly, we store modulations applied to a meta-learned base network as a compressed code for the data. We further quantize and entropy code these modulations, leading to large compression gains while reducing encoding time by two orders of magnitude compared to baselines. We empirically demonstrate the feasibility of our method by compressing various data modalities, from images and audio to medical and climate data.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. LANCE: Locally Adaptive Neural Context Estimation for Overfitted Image Compression

    eess.IV 2026-05 unverdicted novelty 6.0 of 10

    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.

  2. VidFuncta: Towards Generalizable Neural Representations for Ultrasound Videos

    eess.IV 2025-07 conditional novelty 6.0 of 10

    VidFuncta encodes ultrasound videos into static and time-varying latent vectors, improving reconstruction over 2D and 3D baselines while enabling efficient downstream analysis.

  3. Structure-Preserving Patch Decoding for Efficient Neural Video Representation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    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.

  4. How to Design and Train Your Implicit Neural Representation for Video Compression

    cs.CV 2025-06 conditional novelty 5.0 of 10

    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.

Pith tools