Pith. sign in

REVIEW

Raw Image Reconstruction with Learned Compact Metadata

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 2302.12995 v2 pith:DA4LEACE submitted 2023-02-25 cs.CV eess.IV

Raw Image Reconstruction with Learned Compact Metadata

classification cs.CV eess.IV
keywords imageimagesmetadataproposereconstructioncompactnovelproposed
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

While raw images exhibit advantages over sRGB images (e.g., linearity and fine-grained quantization level), they are not widely used by common users due to the large storage requirements. Very recent works propose to compress raw images by designing the sampling masks in the raw image pixel space, leading to suboptimal image representations and redundant metadata. In this paper, we propose a novel framework to learn a compact representation in the latent space serving as the metadata in an end-to-end manner. Furthermore, we propose a novel sRGB-guided context model with improved entropy estimation strategies, which leads to better reconstruction quality, smaller size of metadata, and faster speed. We illustrate how the proposed raw image compression scheme can adaptively allocate more bits to image regions that are important from a global perspective. The experimental results show that the proposed method can achieve superior raw image reconstruction results using a smaller size of the metadata on both uncompressed sRGB images and JPEG images.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.