This paper introduces a novel transformer-based network architecture,
Fl...
We tackle the problem of Tracking Any Point (TAP) in videos, which
speci...
We present DiffRoom, a novel framework for tackling the problem of
high-...
We introduce VideoFlow, a novel optical flow estimation framework for vi...
Event cameras provide high temporal precision, low data rates, and high
...
Local feature matching aims at establishing sparse correspondences betwe...
FlowFormer introduces a transformer architecture into optical flow estim...
Capitalizing on the recent advances in image generation models, existing...
We tackle the problem of estimating correspondences from a general marke...
Capitalizing on the recent advances in image generation models, existing...
We introduce Optical Flow TransFormer (FlowFormer), a transformer-based
...
Visual localization is of great importance in robotics and computer visi...
We tackle the problem of estimating flow between two images with large
l...
Recent learning-based LiDAR odometry methods have demonstrated their
com...