{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-deformable-hypothesis-sampling-for","title":"Learning Deformable Hypothesis Sampling for Accurate PatchMatch Multi-View Stereo","arxiv_id":"2312.15970","date":"2023-12-26","proceeding":null,"authors":["Hongjie Li","Yao Guo","Xianwei Zheng","Hanjiang Xiong"],"abstract":"This paper introduces a learnable Deformable Hypothesis Sampler (DeformSampler) to address the challenging issue of noisy depth estimation for accurate PatchMatch Multi-View Stereo (MVS). We observe that the heuristic depth hypothesis sampling modes employed by PatchMatch MVS solvers are insensitive to (i) the piece-wise smooth distribution of depths across the object surface, and (ii) the implicit multi-modal distribution of depth prediction probabilities along the ray direction on the surface points. Accordingly, we develop DeformSampler to learn distribution-sensitive sample spaces to (i) propagate depths consistent with the scene's geometry across the object surface, and (ii) fit a Laplace Mixture model that approaches the point-wise probabilities distribution of the actual depths along the ray direction. We integrate DeformSampler into a learnable PatchMatch MVS system to enhance depth estimation in challenging areas, such as piece-wise discontinuous surface boundaries and weakly-textured regions. Experimental results on DTU and Tanks \\& Temples datasets demonstrate its superior performance and generalization capabilities compared to state-of-the-art competitors. Code is available at https://github.com/Geo-Tell/DS-PMNet.","url_abs":"https://arxiv.org/abs/2312.15970v1","url_pdf":"https://arxiv.org/pdf/2312.15970v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"learning-deformable-hypothesis-sampling-for","repo_url":"https://github.com/geo-tell/ds-pmnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"depth-prediction","task_name":"Depth Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.15970","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}