Year: 2025
Type: preprint
Abstract: Multi-view camera systems enable rich observations of complex real-world scenes, and understanding dynamic objects in multi-view settings has become central to various applications. In this work, we present MV-TAP, a novel point tracker that tracks points across multi-view videos of dynamic scenes by leveraging cross-view information. MV-TAP utilizes camera geometry and a cross-view attention mechanism to aggregate spatio-temporal information across views, enabling more complete and reliable trajectory estimation in multi-view videos. To support this task, we construct a large-scale synthetic training dataset and real-world evaluation sets tailored for multi-view tracking. Extensive experiments demonstrate that MV-TAP outperforms existing point-tracking methods on challenging benchmarks, establishing an effective baseline for advancing research in multi-view point tracking.
Source: arXiv (Cornell University)
Authors: Koo, Jahyeok, Kim, Inès Hyeonsu, Kim, Mungyeom, Park, Junghyun, Park, Seohyun, Kim, Jaeyeong, Yi, Jung, Cho, Seokju, Kim, Seungryong
Institution: Korea Advanced Institute of Science and Technology
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4416969198
Cites:
Cited by:
Related to: