Pith. sign in

REVIEW 1 cited by

Extreme Image Compression using Fine-tuned VQGANs

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 2307.08265 v3 pith:VAWTO45S submitted 2023-07-17 cs.CV eess.IV

classification cs.CVeess.IV
keywords compressionbitratesframeworkimageperceptualqualitycodebookcoding
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Recent advances in generative compression methods have demonstrated remarkable progress in enhancing the perceptual quality of compressed data, especially in scenarios with low bitrates. However, their efficacy and applicability to achieve extreme compression ratios ($<0.05$ bpp) remain constrained. In this work, we propose a simple yet effective coding framework by introducing vector quantization (VQ)--based generative models into the image compression domain. The main insight is that the codebook learned by the VQGAN model yields a strong expressive capacity, facilitating efficient compression of continuous information in the latent space while maintaining reconstruction quality. Specifically, an image can be represented as VQ-indices by finding the nearest codeword, which can be encoded using lossless compression methods into bitstreams. We propose clustering a pre-trained large-scale codebook into smaller codebooks through the K-means algorithm, yielding variable bitrates and different levels of reconstruction quality within the coding framework. Furthermore, we introduce a transformer to predict lost indices and restore images in unstable environments. Extensive qualitative and quantitative experiments on various benchmark datasets demonstrate that the proposed framework outperforms state-of-the-art codecs in terms of perceptual quality-oriented metrics and human perception at extremely low bitrates ($\le 0.04$ bpp). Remarkably, even with the loss of up to $20\%$ of indices, the images can be effectively restored with minimal perceptual loss.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Generative Latent Coding for Ultra-Low Bitrate Image and Video Compression

    eess.IV 2025-05 conditional novelty 5.0 of 10

    Transform coding in a VQ-VAE latent space, instead of pixel space, yields 45% bitrate savings over MS-ILLM at equal FID for images and 65.3% DISTS-based bitrate savings over PLVC for video at ultra-low bitrates.

Pith tools