CogStereo: Neural Stereo Matching with Implicit Spatial Cognition Embedding

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Fang, Lihuang, Hu, Xiao, Zou, Yuchen, Zhang, Hong
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912669926162432
author Fang, Lihuang
Hu, Xiao
Zou, Yuchen
Zhang, Hong
author_facet Fang, Lihuang
Hu, Xiao
Zou, Yuchen
Zhang, Hong
contents Deep stereo matching has advanced significantly on benchmark datasets through fine-tuning but falls short of the zero-shot generalization seen in foundation models in other vision tasks. We introduce CogStereo, a novel framework that addresses challenging regions, such as occlusions or weak textures, without relying on dataset-specific priors. CogStereo embeds implicit spatial cognition into the refinement process by using monocular depth features as priors, capturing holistic scene understanding beyond local correspondences. This approach ensures structurally coherent disparity estimation, even in areas where geometry alone is inadequate. CogStereo employs a dual-conditional refinement mechanism that combines pixel-wise uncertainty with cognition-guided features for consistent global correction of mismatches. Extensive experiments on Scene Flow, KITTI, Middlebury, ETH3D, EuRoc, and real-world demonstrate that CogStereo not only achieves state-of-the-art results but also excels in cross-domain generalization, shifting stereo vision towards a cognition-driven approach.
format Preprint
id arxiv_https___arxiv_org_abs_2510_22119
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CogStereo: Neural Stereo Matching with Implicit Spatial Cognition Embedding
Fang, Lihuang
Hu, Xiao
Zou, Yuchen
Zhang, Hong
Computer Vision and Pattern Recognition
Deep stereo matching has advanced significantly on benchmark datasets through fine-tuning but falls short of the zero-shot generalization seen in foundation models in other vision tasks. We introduce CogStereo, a novel framework that addresses challenging regions, such as occlusions or weak textures, without relying on dataset-specific priors. CogStereo embeds implicit spatial cognition into the refinement process by using monocular depth features as priors, capturing holistic scene understanding beyond local correspondences. This approach ensures structurally coherent disparity estimation, even in areas where geometry alone is inadequate. CogStereo employs a dual-conditional refinement mechanism that combines pixel-wise uncertainty with cognition-guided features for consistent global correction of mismatches. Extensive experiments on Scene Flow, KITTI, Middlebury, ETH3D, EuRoc, and real-world demonstrate that CogStereo not only achieves state-of-the-art results but also excels in cross-domain generalization, shifting stereo vision towards a cognition-driven approach.
title CogStereo: Neural Stereo Matching with Implicit Spatial Cognition Embedding
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.22119