Saved in:
Bibliographic Details
Main Authors: Rahim, Rafia, Woerz, Samuel, Zell, Andreas
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.18557
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913754253361152
author Rahim, Rafia
Woerz, Samuel
Zell, Andreas
author_facet Rahim, Rafia
Woerz, Samuel
Zell, Andreas
contents Recently, end-to-end deep networks based stereo matching methods, mainly because of their performance, have gained popularity. However, this improvement in performance comes at the cost of increased computational and memory bandwidth requirements, thus necessitating specialized hardware (GPUs); even then, these methods have large inference times compared to classical methods. This limits their applicability in real-world applications. Although we desire high accuracy stereo methods albeit with reasonable inference time. To this end, we propose a fast end-to-end stereo matching method. Majority of this speedup comes from integrating a leaner backbone. To recover the performance lost because of a leaner backbone, we propose to use learned attention weights based cost volume combined with LogL1 loss for stereo matching. Using LogL1 loss not only improves the overall performance of the proposed network but also leads to faster convergence. We do a detailed empirical evaluation of different design choices and show that our method requires 4x less operations and is also about 9 to 14x faster compared to the state of the art methods like ACVNet [1], LEAStereo [2] and CFNet [3] while giving comparable performance.
format Preprint
id arxiv_https___arxiv_org_abs_2503_18557
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LeanStereo: A Leaner Backbone based Stereo Network
Rahim, Rafia
Woerz, Samuel
Zell, Andreas
Computer Vision and Pattern Recognition
Recently, end-to-end deep networks based stereo matching methods, mainly because of their performance, have gained popularity. However, this improvement in performance comes at the cost of increased computational and memory bandwidth requirements, thus necessitating specialized hardware (GPUs); even then, these methods have large inference times compared to classical methods. This limits their applicability in real-world applications. Although we desire high accuracy stereo methods albeit with reasonable inference time. To this end, we propose a fast end-to-end stereo matching method. Majority of this speedup comes from integrating a leaner backbone. To recover the performance lost because of a leaner backbone, we propose to use learned attention weights based cost volume combined with LogL1 loss for stereo matching. Using LogL1 loss not only improves the overall performance of the proposed network but also leads to faster convergence. We do a detailed empirical evaluation of different design choices and show that our method requires 4x less operations and is also about 9 to 14x faster compared to the state of the art methods like ACVNet [1], LEAStereo [2] and CFNet [3] while giving comparable performance.
title LeanStereo: A Leaner Backbone based Stereo Network
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.18557