LDMIC：基于学习的分布式多视图图像编码
LDMIC: Learning-based Distributed Multi-view Image Coding
AI总结：
本文提出基于学习的分布式多视图图像编码框架LDMIC，通过独立编码和基于交叉注意力的联合上下文传递模块实现联合解码，在快速编码的同时显著优于现有多视图图像编码方法。
摘要：
多视图图像压缩在三维相关应用中起着关键作用。现有方法采用预测编码架构，需要联合编码来压缩相应的视差以及残差信息。这要求相机之间进行协作，并在不同视图之间施加对极几何约束，这使得这些方法难以部署在具有随机重叠视场的分布式相机系统中。与此同时，分布式信源编码理论表明，相关信源的高效数据压缩可以通过独立编码和联合解码来实现，这促使我们设计了一个基于学习的分布式多视图图像编码（LDMIC）框架。在独立编码器的基础上，LDMIC 在解码器端引入了一个基于交叉注意力机制的简单而有效的联合上下文传递模块，以有效捕获全局视图间相关性，该模块对图像之间的几何关系不敏感。实验结果表明，LDMIC 显著优于传统和基于学习的多视图图像编码方法，同时具有快速的编码速度。代码将在 https://github.com/Xinjie-Q/LDMIC 发布。
英文摘要：
Multi-view image compression plays a critical role in 3D-related applications. Existing methods adopt a predictive coding architecture, which requires joint encoding to compress the corresponding disparity as well as residual information. This demands collaboration among cameras and enforces the epipolar geometric constraint between different views, which makes it challenging to deploy these methods in distributed camera systems with randomly overlapping fields of view. Meanwhile, distributed source coding theory indicates that efficient data compression of correlated sources can be achieved by independent encoding and joint decoding, which motivates us to design a learning-based distributed multi-view image coding (LDMIC) framework. With independent encoders, LDMIC introduces a simple yet effective joint context transfer module based on the cross-attention mechanism at the decoder to effectively capture the global inter-view correlations, which is insensitive to the geometric relationships between images. Experimental results show that LDMIC significantly outperforms both traditional and learning-based MIC methods while enjoying fast encoding speed. Code will be released at https://github.com/Xinjie-Q/LDMIC.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
