Deep learning has made substantial breakthroughs in many fields due to its powerful
automatic representation capabilities. It has been proven that neural architecture design is …

In the realm of modern autonomous driving, the perception system is indispensable for
accurately assessing the state of the surrounding environment, thereby enabling informed …

Abstract Recurrent All-Pairs Field Transforms (RAFT) has shown great potentials in
matching tasks. However, all-pairs correlations lack non-local geometry knowledge and …

We present a unified formulation and model for three motion and 3D perception tasks:
optical flow, rectified stereo matching and unrectified stereo depth estimation from posed …

With the advent of convolutional neural networks, stereo matching algorithms have recently
gained tremendous progress. However, it remains a great challenge to accurately extract …

Stereo matching is a fundamental building block for many vision and robotics applications.
An informative and concise cost volume representation is vital for stereo matching of high …

We introduce RAFT-Stereo, a new deep architecture for rectified stereo based on the optical
flow network RAFT [35]. We introduce multi-level convolutional GRUs, which more efficiently …

Recently, the ever-increasing capacity of large-scale annotated datasets has led to profound
progress in stereo matching. However, most of these successes are limited to a specific …

Stereo matching methods based on iterative optimization like RAFT-Stereo and IGEV-Stereo
have evolved into a cornerstone in the field of stereo matching. However these methods …

Despite impressive performance for high-level downstream tasks, self-supervised pre-
training methods have not yet fully delivered on dense geometric vision tasks such as stereo …