视差对齐一切：面向分布式多视图图像压缩的全视差注意力机制
Parallax to Align Them All: An OmniParallax Attention Mechanism for Distributed Multi-View Image Compression
OPAM 提供了一种显式建模任意两路信息源相关性的通用注意力机制，可复用于多视图立体、光场处理等需要跨视图对齐的任务；其分布式解码框架也为多相机系统下的低带宽传输提供了新思路。
原文依据 we propose a novel OmniParallax Attention Mechanism (OPAM), which is a general mechanism for explicitly modeling correlations and aligned features between arbitrary pairs of information sources.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论多视图图像压缩（MIC）旨在通过利用图像间相关性实现高压缩效率，在三维应用中起着关键作用。作为MIC的子领域，分布式多视图图像压缩（DMIC）在无需编码器端视图间信息的情况下即可获得与MIC相当的性能。然而，现有DMIC方法通常平等对待所有图像，忽略了解码过程中不同视图之间相关性的差异，导致编码性能次优。为解决这一局限，我们提出了一种新颖的全视差注意力机制（OPAM），这是一种显式建模任意信息源对之间相关性和对齐特征的通用机制。基于OPAM，我们提出了视差多信息融合模块（PMIFM），以自适应地整合来自不同信息源的信息。PMIFM被集成到联合解码器和熵模型中，以构建我们的端到端DMIC框架ParaHydra。大量实验表明，ParaHydra是首个显著超越最优MIC编解码器的DMIC方法，同时保持较低的计算开销。随着输入视图数量的增加，性能增益更加明显。与LDMIC相比，ParaHydra在WildTrack(3)上实现了19.72%的码率节省，在WildTrack(6)上高达24.18%，同时显著提升了编码效率（解码速度提升高达65倍，编码速度提升高达34倍）。
英文原文摘要 1505 字符
Multi-view image compression (MIC) aims to achieve high compression efficiency by exploiting inter-image correlations, playing a crucial role in 3D applications. As a subfield of MIC, distributed multi-view image compression (DMIC) offers performance comparable to MIC while eliminating the need for inter-view information at the encoder side.However, existing methods in DMIC typically treat all images equally, overlooking the varying degrees of correlation between different views during decoding, which leads to suboptimal coding performance. To address this limitation, we propose a novel OmniParallax Attention Mechanism (OPAM), which is a general mechanism for explicitly modeling correlations and aligned features between arbitrary pairs of information sources.Building upon OPAM, we propose a Parallax Multi Information Fusion Module (PMIFM) to adaptively integrate information from different sources. PMIFM is incorporated into both the joint decoder and the entropy model to construct our end-to-end DMIC framework, ParaHydra.Extensive experiments demonstrate that ParaHydra is the first DMIC method to significantly surpass state-of-the-art MIC codecs, while maintaining low computational overhead. Performance gains become more pronounced as the number of input views increases. Compared with LDMIC, ParaHydra achieves bitrate savings of 19.72\% on WildTrack(3) and up to 24.18\% on WildTrack(6), while significantly improving coding efficiency (as much as 65xin decoding and 34xin encoding).