Geometry-guided compact compression for light field image using graph convolutional networks

Yu Liu, Linhui Wei, Heming Zhao, Jingming Shan, Yumei Wang
2022 Proceedings of the 32nd Workshop on Network and Operating Systems Support for Digital Audio and Video  
Light field records the information of the light in space and contributes to regenerate the content effectively, which makes immersive media more promising. In this paper, we propose a geometryguided compact compression scheme (GCC) for light field image. We regard that the geometry of GCC includes the structure in a single sub-aperture image (SAI) and the relationship among SAIs, which can be used to fully explore the compact representation for light field image. The light field image is
more » ... d into key SAIs and non-key SAIs. The key SAIs are obtained by down-sampling in the angular domain and arranged into the pseudo-sequence that needs to be compressed. We consider the superpixel-based segmentation algorithm to detect the contours and obtain the sketch map for the non-key SAIs. Meanwhile, the graph model is used to establish the relationships among the SAIs by the vertices and edges. On the decoder side, the light field image is reconstructed by the graph convolutional networks, and the sketch map optimizes the details of the recovered images to some extent. Experimental results show the benefit of GCC in terms of rate-distortion performances compare with several state-of-the-art methods for the real-world and synthetic light field datasets. Besides, the proposed GCC is able to generalize over datasets not seen during training. CCS CONCEPTS • Computing methodologies → Virtual reality; Image compression.
doi:10.1145/3534088.3534345 fatcat:zxu6rluhlraongev2sgc3a2apu