Stereo vision is a flourishing field, attracting the attention of many researchers. Recently,
leveraging on the development of deep learning, stereo matching algorithms have achieved …

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

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 …

In the field of binocular stereo matching, remarkable progress has been made by iterative
methods like RAFT-Stereo and CREStereo. However, most of these methods lose …

This paper presents HITNet, a novel neural network architecture for real-time stereo
matching. Contrary to many recent neural network approaches that operate on a full …

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 …

We explore the problem of real-time stereo matching on high-res imagery. Many state-of-the-
art (SOTA) methods struggle to process high-res imagery because of memory constraints or …

Stereo matching is a core task for many computer vision and robotics applications. Despite
their dominance in traditional stereo methods the hand-crafted Markov Random Field (MRF) …

Low-precision floating-point arithmetic is a powerful tool for accelerating scientific computing
applications, especially those in artificial intelligence. Here, we present an investigation …

Estimating disparities in challenging areas is difficult and limits the performance of stereo
matching models. In this paper we exploit local structure information (LSI) to enhance stereo …