通过注意力调优增强立体匹配的全局上下文，提升复杂场景下的精度。
Global Regulation and Excitation via Attention Tuning for Stereo Matching
- 设计三种注意力模块，分别捕捉空间、视差线和体积维度的全局信息。
- 在KITTI 2015、ETH3D等数据集上超越现有方法，部分排名第一。
- 可集成到多种迭代立体匹配模型中，适用于复杂纹理或遮挡场景。
立体匹配在迭代算法如RAFT-Stereo和IGEV-Stereo的推动下取得显著进展。然而，在存在遮挡、无纹理或重复模式的病态区域，这些方法因缺乏全局上下文与几何信息而难以有效迭代优化。为此，我们提出全局调节与激励注意力调优（GREAT）框架，包含三个注意力模块：空间注意力（SA）捕获空间维度的全局上下文，匹配注意力（MA）沿极线提取全局信息，体积注意力（VA）协同前两者构建由全局上下文与几何细节激发的更鲁棒代价体。为验证该框架的通用性与有效性，我们将它集成至多个代表性迭代立体匹配方法中，统称为GREAT-Stereo。实验表明，该框架在挑战性病态区域表现优异。应用于IGEV-Stereo时，GREAT-IGEV在场景流测试集、KITTI 2015、ETH3D排行榜上位列第一，于Middlebury基准上位居第二。代码已开源：https://github.com/JarvisLee0423/GREAT-Stereo。
原文摘要 · Abstract (English)
Stereo matching achieves significant progress with iterative algorithms like RAFT-Stereo and IGEV-Stereo. However, these methods struggle in ill-posed regions with occlusions, textureless, or repetitive patterns, due to a lack of global context and geometric information for effective iterative refinement. To enable the existing iterative approaches to incorporate global context, we propose the Global Regulation and Excitation via Attention Tuning (GREAT) framework which encompasses three attention modules. Specifically, Spatial Attention (SA) captures the global context within the spatial dimension, Matching Attention (MA) extracts global context along epipolar lines, and Volume Attention (VA) works in conjunction with SA and MA to construct a more robust cost-volume excited by global context and geometric details. To verify the universality and effectiveness of this framework, we integrate it into several representative iterative stereo-matching methods and validate it through extensive experiments, collectively denoted as GREAT-Stereo. This framework demonstrates superior performance in challenging ill-posed regions. Applied to IGEV-Stereo, among all published methods, our GREAT-IGEV ranks first on the Scene Flow test set, KITTI 2015, and ETH3D leaderboards, and achieves second on the Middlebury benchmark. Code is available at https://github.com/JarvisLee0423/GREAT-Stereo.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。