Papers2

#cross-view correspondence

Learning Cross-View Object Correspondence via Cycle-Consistent Mask Prediction

Shannan Yan, Leqi Zheng et al.Feb 22arXiv

This paper teaches a computer to find the same object when seen from two very different cameras, like a body camera (first-person) and a room camera (third-person).

#cross-view correspondence#egocentric to exocentric#binary segmentation

3AM: 3egment Anything with Geometric Consistency in Videos

Intermediate

Yang-Che Sun, Cheng Sun et al.Jan 13arXiv

3AM is a new way to track and segment the same object across a whole video, even when the camera view changes a lot.

#video object segmentation#SAM2#geometry-aware tracking