用超像素软约束提升立体匹配边界精度
Superpixel Cost Volume Excitation for Stereo Matching
- 引入超像素软约束，强化局部一致性
- 显著改善预测视差图在物体边界的准确性
- 适合关注立体匹配细节优化的研究者
本文聚焦于通过引入超像素软约束来激发立体匹配的内在局部一致性，旨在缓解预测视差图在边界处的不准确问题。研究发现，超像素内的邻近像素更可能属于同一物体且强度相似。基于此，方法促使网络在每个超像素内生成一致的视差概率分布，从而提升整体视差图的准确性和连贯性。在多个主流数据集上的实验验证了该方法的有效性，表明其能帮助基于代价体积的匹配网络恢复具有竞争力的性能。
原文摘要 · Abstract (English)
In this work, we concentrate on exciting the intrinsic local consistency of stereo matching through the incorporation of superpixel soft constraints, with the objective of mitigating inaccuracies at the boundaries of predicted disparity maps. Our approach capitalizes on the observation that neighboring pixels are predisposed to belong to the same object and exhibit closely similar intensities within the probability volume of superpixels. By incorporating this insight, our method encourages the network to generate consistent probability distributions of disparity within each superpixel, aiming to improve the overall accuracy and coherence of predicted disparity maps. Experimental evalua tions on widely-used datasets validate the efficacy of our proposed approach, demonstrating its ability to assist cost volume-based matching networks in restoring competitive performance.
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。