通过循环一致性掩码预测学习跨视角物体对应关系
Learning Cross-View Object Correspondence via Cycle-Consistent Mask Prediction
AI总结：
本文提出基于条件二值分割的框架，通过循环一致性训练目标视角预测掩码并重建源视角掩码，实现无标注的自监督学习，提升跨视角物体对应性能。
摘要：
我们研究了在视频中建立不同视角下物体级视觉对应关系的任务，重点关注具有挑战性的以自身为中心到外部视角以及外部视角到自身为中心的场景。我们提出了一种基于条件二值分割的简单而有效的框架，其中物体查询掩码被编码到潜在表示中以引导目标视频中相应物体的定位。为了鼓励鲁棒且视角不变的表示，我们引入了循环一致性训练目标：目标视角预测的掩码被投影回源视角以重建原始查询掩码。这种双向约束在不需要地面真实标注的情况下提供了强大的自监督信号，并在推理时启用测试时间训练（TTT）。在Ego-Exo4D和HANDAL-X基准测试中，实验展示了我们优化目标和TTT策略的有效性，取得了最先进的性能。代码可在https://github.com/shannany0606/CCMP获取。
英文摘要：
We study the task of establishing object-level visual correspondence across different viewpoints in videos, focusing on the challenging egocentric-to-exocentric and exocentric-to-egocentric scenarios. We propose a simple yet effective framework based on conditional binary segmentation, where an object query mask is encoded into a latent representation to guide the localization of the corresponding object in a target video. To encourage robust, view-invariant representations, we introduce a cycle-consistency training objective: the predicted mask in the target view is projected back to the source view to reconstruct the original query mask. This bidirectional constraint provides a strong self-supervisory signal without requiring ground-truth annotations and enables test-time training (TTT) at inference. Experiments on the Ego-Exo4D and HANDAL-X benchmarks demonstrate the effectiveness of our optimization objective and TTT strategy, achieving state-of-the-art performance. The code is available at https://github.com/shannany0606/CCMP.
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。
