Papers
arxiv:2403.00628

Region-Adaptive Transform with Segmentation Prior for Image Compression

Published on Mar 1, 2024
Authors:
,
,
,
,

Abstract

Learned Image Compression (LIC) has shown remarkable progress in recent years. Existing works commonly employ CNN-based or self-attention-based modules as transform methods for compression. However, there is no prior research on neural transform that focuses on specific regions. In response, we introduce the class-agnostic segmentation masks (i.e. semantic masks without category labels) for extracting region-adaptive contextual information. Our proposed module, Region-Adaptive Transform, applies adaptive convolutions on different regions guided by the masks. Additionally, we introduce a plug-and-play module named Scale Affine Layer to incorporate rich contexts from various regions. While there have been prior image compression efforts that involve segmentation masks as additional intermediate inputs, our approach differs significantly from them. Our advantages lie in that, to avoid extra bitrate overhead, we treat these masks as privilege information, which is accessible during the model training stage but not required during the inference phase. To the best of our knowledge, we are the first to employ class-agnostic masks as privilege information and achieve superior performance in pixel-fidelity metrics, such as Peak Signal to Noise Ratio (PSNR). The experimental results demonstrate our improvement compared to previously well-performing methods, with about 8.2% bitrate saving compared to VTM-17.0. The source code is available at https://github.com/GityuxiLiu/SegPIC-for-Image-Compression.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2403.00628 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2403.00628 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2403.00628 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.