Continuous Patch Stitching for Block-wise Image Compression
Zifu Zhang, Shengxi Li, Henan Liu, Mai Xu, Ce Zhu

TL;DR
This paper introduces a continuous patch stitching framework for block-wise image compression that reduces computational resources and eliminates block artifacts, enabling seamless high-quality image compression.
Contribution
It proposes a novel CPS framework with padding-free operations and a stitching strategy, improving efficiency and artifact removal in block-wise learned image compression.
Findings
Achieves state-of-the-art performance on image compression benchmarks.
Requires less than half the computational resources of existing models.
Effectively eliminates block artifacts in high-resolution image compression.
Abstract
Most recently, learned image compression methods have outpaced traditional hand-crafted standard codecs. However, their inference typically requires to input the whole image at the cost of heavy computing resources, especially for high-resolution image compression; otherwise, the block artefact can exist when compressed by blocks within existing learned image compression methods. To address this issue, we propose a novel continuous patch stitching (CPS) framework for block-wise image compression that is able to achieve seamlessly patch stitching and mathematically eliminate block artefact, thus capable of significantly reducing the required computing resources when compressing images. More specifically, the proposed CPS framework is achieved by padding-free operations throughout, with a newly established parallel overlapping stitching strategy to provide a general upper bound for…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Data Compression Techniques · Video Coding and Compression Technologies · Advanced Vision and Imaging
