Learning Parallax Transformer Network for Stereo Image JPEG Artifacts Removal
This addresses the problem of improving image quality in stereo JPEG compression for applications like 3D imaging, though it is incremental as it builds on existing stereo and artifact removal techniques.
The paper tackles stereo image JPEG artifacts removal by exploiting information from both views, proposing a parallax transformer network that achieves superior performance compared to state-of-the-art methods.
Under stereo settings, the performance of image JPEG artifacts removal can be further improved by exploiting the additional information provided by a second view. However, incorporating this information for stereo image JPEG artifacts removal is a huge challenge, since the existing compression artifacts make pixel-level view alignment difficult. In this paper, we propose a novel parallax transformer network (PTNet) to integrate the information from stereo image pairs for stereo image JPEG artifacts removal. Specifically, a well-designed symmetric bi-directional parallax transformer module is proposed to match features with similar textures between different views instead of pixel-level view alignment. Due to the issues of occlusions and boundaries, a confidence-based cross-view fusion module is proposed to achieve better feature fusion for both views, where the cross-view features are weighted with confidence maps. Especially, we adopt a coarse-to-fine design for the cross-view interaction, leading to better performance. Comprehensive experimental results demonstrate that our PTNet can effectively remove compression artifacts and achieves superior performance than other testing state-of-the-art methods.