{"ID":2875492,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.02415","arxiv_id":"2509.02415","title":"Decoupling Bidirectional Geometric Representations of 4D cost volume with 2D convolution","abstract":"High-performance real-time stereo matching methods invariably rely on 3D regularization of the cost volume, which is unfriendly to mobile devices. And 2D regularization based methods struggle in ill-posed regions. In this paper, we present a deployment-friendly 4D cost aggregation network DBStereo, which is based on pure 2D convolutions. Specifically, we first provide a thorough analysis of the decoupling characteristics of 4D cost volume. And design a lightweight bidirectional geometry aggregation block to capture spatial and disparity representation respectively. Through decoupled learning, our approach achieves real-time performance and impressive accuracy simultaneously. Extensive experiments demonstrate that our proposed DBStereo outperforms all existing aggregation-based methods in both inference time and accuracy, even surpassing the iterative-based method IGEV-Stereo. Our study break the empirical design of using 3D convolutions for 4D cost volume and provides a simple yet strong baseline of the proposed decouple aggregation paradigm for further study. Code will be available at (\\href{https://github.com/happydummy/DBStereo}{https://github.com/happydummy/DBStereo}) soon.","short_abstract":"High-performance real-time stereo matching methods invariably rely on 3D regularization of the cost volume, which is unfriendly to mobile devices. And 2D regularization based methods struggle in ill-posed regions. In this paper, we present a deployment-friendly 4D cost aggregation network DBStereo, which is based on pu...","url_abs":"https://arxiv.org/abs/2509.02415","url_pdf":"https://arxiv.org/pdf/2509.02415v1","authors":"[\"Xiaobao Wei\",\"Changyong Shu\",\"Zhaokun Yue\",\"Chang Huang\",\"Weiwei Liu\",\"Shuai Yang\",\"Lirong Yang\",\"Peng Gao\",\"Wenbin Zhang\",\"Gaochao Zhu\",\"Chengxiang Wang\"]","published":"2025-09-02T15:21:49Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":610215,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2875492,"paper_url":"https://arxiv.org/abs/2509.02415","paper_title":"Decoupling Bidirectional Geometric Representations of 4D cost volume with 2D convolution","repo_url":"https://github.com/happydummy/DBStereo","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}