Deep learning-based intelligent vehicle perception has been developing prominently in
recent years to provide a reliable source for motion planning and decision making in …

We introduce a novel framework for training deep stereo networks effortlessly and without
any ground-truth. By leveraging state-of-the-art neural rendering solutions, we generate …

Deep learning-based stereo matching methods have made remarkable progress in recent
years. However, it is still a challenging task to achieve high accuracy in real time. In …

Abstract Recently, deep Stereo Matching (SM) networks have shown impressive
performance and attracted increasing attention in computer vision. However, existing deep …

Due to the domain differences and unbalanced disparity distribution across multiple
datasets, current stereo matching approaches are commonly limited to a specific dataset …

We introduce a novel approach for adapting deep stereo networks in a collaborative
manner. By building over principles of federated learning we develop a distributed …

This paper proposes a novel framework integrating the principles of active stereo in
standard passive camera systems without a physical pattern projector. We virtually project a …

Dynamic stereo matching is the task of estimating consistent disparities from stereo videos
with dynamic objects. Recent learning-based methods prioritize optimal performance on a …

Stereo matching is a core component in many computer vision and robotics systems.
Despite significant advances over the last decade, handling matching ambiguities in ill …

Estimating depth from images nowadays yields outstanding results, both in terms of in-
domain accuracy and generalization. However, we identify two main challenges that remain …