paper-with-me

Papers

Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching

2024-03-01 · CVPR 2024 1 · Xianqi Wang, Gangwei Xu, Hao Jia, Xin Yang

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 struggle to simultaneously capture high-frequency information in edges and low-frequency information in smooth regions due to the fixed receptive field. As a result, they tend to lose details, blur edges, and produce false matches in textureless areas. In this paper, we propose Selective Recurrent Unit (SRU), a novel iterative update operator for stereo matching. The SRU module can adaptively fuse hidden disparity information at multiple frequencies for edge and smooth regions. To perform adaptive fusion, we introduce a new Contextual Spatial Attention (CSA) module to generate attention maps as fusion weights. The SRU empowers the network to aggregate hidden disparity information across multiple frequencies, mitigating the risk of vital hidden disparity information loss during iterative processes. To verify SRU's universality, we apply it to representative iterative stereo matching methods, collectively referred to as Selective-Stereo. Our Selective-Stereo ranks $1^{st}$ on KITTI 2012, KITTI 2015, ETH3D, and Middlebury leaderboards among all published methods. Code is available at https://github.com/Windsrain/Selective-Stereo.

📄 PDF Abstract BibTeX arXiv:2403.00486

Code (1)

windsrain/selective-stereo 공식 구현 pytorch

Tasks

Stereo Matching

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Highway Layer 설명 없음
SRU SRU, or Simple Recurrent Unit, is a recurrent neural unit with a light form of recurrence. SRU exhibits the same level of parallelism as…

Similar Papers 제목 키워드 기반

Learning Accurate and Enriched Features for Stereo Image Super-Resolution

2024-06-23 · Hu Gao, Depeng Dang

Stereo image super-resolution (stereoSR) aims to enhance the quality of super-resolution results by incorporating complementary information from an alternative view. Although current methods have shown significant advanc…

Image Super-ResolutionStereo Image Super-ResolutionSuper-Resolution

MAFNet:Multi-frequency Adaptive Fusion Network for Real-time Stereo Matching

2025-12-04 · Ao Xu, Rujin Zhao, Xiong Xu, Boceng Huang 외 arxiv

Existing stereo matching networks typically rely on either cost-volume construction based on 3D convolutions or deformation methods based on iterative optimization. The former incurs significant computational overhead du…

Disparity Estimation

Wireless Communications in Doubly Selective Channels with Domain Adaptivity

2024-07-31 · J. Andrew Zhang, Hongyang Zhang, Kai Wu, Xiaojing Huang 외

Wireless communications are significantly impacted by the propagation environment, particularly in doubly selective channels with variations in both time and frequency domains. Orthogonal Time Frequency Space (OTFS) modu…

StereoGen: High-quality Stereo Image Generation from a Single Image

2025-01-15 · Xianqi Wang, Hao Yang, Gangwei Xu, Junda Cheng 외

State-of-the-art supervised stereo matching methods have achieved amazing results on various benchmarks. However, these data-driven methods suffer from generalization to real-world scenarios due to the lack of real-world…

Depth EstimationImage GenerationMonocular Depth EstimationStereo Matching+1

Learning Robust Stereo Matching in the Wild with Selective Mixture-of-Experts

2025-07-07 · Yun Wang, Longguang Wang, Chenghao Zhang, Yongjian Zhang 외

Recently, learning-based stereo matching networks have advanced significantly. However, they often lack robustness and struggle to achieve impressive cross-domain performance due to domain shifts and imbalanced disparity…

Inductive BiasMixture-of-ExpertsStereo Matching