Pith. sign in

REVIEW 8 cited by

CompressAI: a PyTorch library and evaluation platform for end-to-end compression research

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

arxiv 2011.03029 v1 pith:QYN64FIA submitted 2020-11-05 cs.CV eess.IV

classification cs.CVeess.IV
keywords compressionmodelscompressaiend-to-endcodecsevaluationimagelearned
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper presents CompressAI, a platform that provides custom operations, layers, models and tools to research, develop and evaluate end-to-end image and video compression codecs. In particular, CompressAI includes pre-trained models and evaluation tools to compare learned methods with traditional codecs. Multiple models from the state-of-the-art on learned end-to-end compression have thus been reimplemented in PyTorch and trained from scratch. We also report objective comparison results using PSNR and MS-SSIM metrics vs. bit-rate, using the Kodak image dataset as test set. Although this framework currently implements models for still-picture compression, it is intended to be soon extended to the video compression domain.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

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

  1. Compress-Align-Detect: onboard change detection from unregistered images

    cs.CV 2025-07 conditional novelty 7.0 of 10

    A single neural network performs compression, co-registration, and change detection onboard a satellite, achieving F1 up to about 70% at low bitrates on simulated unregistered image pairs.

  2. LotteryCodec: Searching the Implicit Representation in a Random Network for Low-Complexity Image Compression

    eess.IV 2025-07 conditional novelty 7.0 of 10

    LotteryCodec compresses an image into a binary mask and small modulations for a frozen random network, achieving better rate-distortion than VTM with two orders of magnitude fewer decoding operations.

  3. ReGenVC: End-to-End Real-Time Generative Video Coding at Ultra-Low Bitrate

    eess.IV 2026-07 conditional novelty 6.0 of 10

    A pose-and-reference generative talking-head codec hits ~10× lower bitrate than x264/x265 and real-time 24 fps decode on an 8-GPU node via 4-step distillation plus multi-GPU systems tricks.

  4. Wavefront Parallelization for Efficient Learned Image Compression

    eess.IV 2026-07 conditional novelty 6.0 of 10

    A staggered wavefront schedule, proved optimal via Lamport's method, accelerates pre-trained spatial autoregressive learned image codecs roughly 13-32x with unchanged rate-distortion.

  5. End-to-End RGB-IR Joint Image Compression With Channel-wise Cross-modality Entropy Model

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A channel-wise cross-modality entropy model with low-frequency context fusion improves joint RGB-IR image compression, achieving 23.1% bit rate savings over the previous state of the art on LLVIP.

  6. Flexible Mixed Precision Quantization for Learned Image Compression

    eess.IV 2025-06 conditional novelty 6.0 of 10

    A rate-distortion sensitivity criterion assigns per-layer bit-widths, yielding about 1 to 2 percent BD-Rate improvement over 8-bit fixed-precision quantization at matched model size for learned image compression.

  7. GSCodec Studio: A Modular Framework for Gaussian Splat Compression

    cs.CV 2025-06 conditional novelty 5.0 of 10

    GSCodec Studio is a modular open-source framework for Gaussian Splat compression, and its composed Static and Dynamic GSCodec pipelines report competitive rate-distortion results against several baselines.

  8. Compress image to patches for Vision Transformer

    cs.CV 2025-02 conditional novelty 5.0 of 10

    Using a frozen learned-compression encoder as the ViT patch embedder yields a 4x token reduction and 63% FLOP savings, with accuracy gains shown only on one small dataset.

Pith tools