Gigapixel videography, beyond the resolution of a single camera and human visual perception, aims to capture large-scale dynamic scenes with extremely high resolution. Benefited from the high resolution and wide FoV, it brings new challenges and opportunities for various computer vision tasks. Among them, multi-object tracking has attracted extensive attention with various solutions including FairMOT, OUTrack_fm, UniTrack, etc.
However, robust and efficient long-term tracking in large-scale scenes remains a challenge, in particular, when the scale and resolution of the scenes reach gigapixel-level. Aiming for these open questions, a novel challenge GigaTracking: When Multi-Object Tracking meets Gigapixel Videography is proposed.
![]() |
Lu Fang |
Tsinghua University |
![]() |
David J. Brady |
University of Arizona |
![]() |
Mengqi Ji |
Beihang University |
![]() |
Feng Yang |
Google Research |