提出多假设匹配框架，提升深度不连续和强缩放场景下的图像匹配精度
Handling Multiple Hypotheses in Coarse-to-Fine Dense Image Matching
- 在每尺度预测多个对应点假设，用束搜索传播
- 引入跨注意力融合多假设，显著减少误匹配
- 适合处理深度边界和大幅缩放的复杂图像对
稠密图像匹配旨在为源图像每个像素找到目标图像中对应的像素。现有先进方法通常采用粗到精机制，每尺度仅生成一个对应假设。但在挑战性场景（如深度不连续或目标图是源图强烈缩放）下，邻近像素的对应点分布广泛，单一假设易导致错误匹配。本文提出在每尺度预测多个对应假设，采用束搜索策略传播多假设，并将其集成至交叉注意力层，构建新型稠密匹配架构BEAMER。该方法可学习在各尺度间保留并传播多假设，显著提升鲁棒性，尤其在深度不连续或强缩放情况下优于现有方法。
原文摘要 · Abstract (English)
Dense image matching aims to find a correspondent for every pixel of a source image in a partially overlapping target image. State-of-the-art methods typically rely on a coarse-to-fine mechanism where a single correspondent hypothesis is produced per source location at each scale. In challenging cases -- such as at depth discontinuities or when the target image is a strong zoom-in of the source image -- the correspondents of neighboring source locations are often widely spread and predicting a single correspondent hypothesis per source location at each scale may lead to erroneous matches. In this paper, we investigate the idea of predicting multiple correspondent hypotheses per source location at each scale instead. We consider a beam search strategy to propagat multiple hypotheses at each scale and propose integrating these multiple hypotheses into cross-attention layers, resulting in a novel dense matching architecture called BEAMER. BEAMER learns to preserve and propagate multiple hypotheses across scales, making it significantly more robust than state-of-the-art methods, especially at depth discontinuities or when the target image is a strong zoom-in of the source image.
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。