Image Matching is a core component of all best-performing algorithms and pipelines in 3D
vision. Yet despite matching being fundamentally a 3D problem, intrinsically linked to …

We introduce SEA-RAFT, a more simple, efficient, and accurate RAFT for optical flow.
Compared with RAFT, SEA-RAFT is trained with a new loss (mixture of Laplace). It directly …

Optical flow estimation a process of predicting pixel-wise displacement between consecutive
frames has commonly been approached as a regression task in the age of deep learning …

In this work we introduce ProMotion a unified prototypical transformer-based framework
engineered to model fundamental motion tasks. ProMotion offers a range of compelling …

Optical flow is a classical task that is important to the vision community. Classical optical flow
estimation uses two frames as input whilst some recent methods consider multiple frames to …

Optical Flow Estimation aims to find the 2D dense motion field between two frames. Due to
the limitation of model structures and training datasets, existing methods often rely too much …

Attention-based motion aggregation concepts have recently shown their usefulness in
optical flow estimation, in particular when it comes to handling occluded regions. However …

Abstract Multi-Object Tracking (MOT) encompasses various tracking scenarios each
characterized by unique traits. Effective trackers should demonstrate a high degree of …

Optical flow estimation is a challenging task consisting of predicting per-pixel motion vectors
between images. Recent methods have employed larger and more complex models to …

Visual Odometry (VO) is vital for the navigation of autonomous systems, providing accurate
position and orientation estimates at reasonable costs. While traditional VO methods excel …