{"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/stereonet-guided-hierarchical-refinement-for","title":"StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction","arxiv_id":"1807.08865","date":"2018-07-24","proceeding":"ECCV 2018 9","authors":["Sameh Khamis","Sean Fanello","Christoph Rhemann","Adarsh Kowdle","Julien Valentin","Shahram Izadi"],"abstract":"This paper presents StereoNet, the first end-to-end deep architecture for\nreal-time stereo matching that runs at 60 fps on an NVidia Titan X, producing\nhigh-quality, edge-preserved, quantization-free disparity maps. A key insight\nof this paper is that the network achieves a sub-pixel matching precision than\nis a magnitude higher than those of traditional stereo matching approaches.\nThis allows us to achieve real-time performance by using a very low resolution\ncost volume that encodes all the information needed to achieve high disparity\nprecision. Spatial precision is achieved by employing a learned edge-aware\nupsampling function. Our model uses a Siamese network to extract features from\nthe left and right image. A first estimate of the disparity is computed in a\nvery low resolution cost volume, then hierarchically the model re-introduces\nhigh-frequency details through a learned upsampling function that uses compact\npixel-to-pixel refinement networks. Leveraging color input as a guide, this\nfunction is capable of producing high-quality edge-aware output. We achieve\ncompelling results on multiple benchmarks, showing how the proposed method\noffers extreme flexibility at an acceptable computational budget.","url_abs":"http://arxiv.org/abs/1807.08865v1","url_pdf":"http://arxiv.org/pdf/1807.08865v1.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":"stereonet-guided-hierarchical-refinement-for","repo_url":"https://github.com/andrewlstewart/StereoNet_PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"stereonet-guided-hierarchical-refinement-for","repo_url":"https://github.com/meteorshowers/StereoNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"depth-prediction","task_name":"Depth Prediction"},{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"stereo-depth-estimation","task_name":"Stereo Depth Estimation"},{"task_slug":"stereo-matching-1","task_name":"Stereo Matching"},{"task_slug":"stereo-matching","task_name":"Stereo Matching Hand"}],"methods":[{"method_slug":"siamese-network","method_name":"Siamese Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/stereo-depth-estimation-on-sceneflow","task":"Stereo Depth Estimation","dataset":"sceneflow","model":"stereonet","rank_in_archive_order":2,"of":3,"metrics":{"Average End-Point Error":"1.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.08865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.08865"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/meteorshowers/StereoNet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/andrewlstewart/StereoNet_PyTorch","reach":null}],"summary":{"ran_draft_wrong":3,"unverified":4},"by_repo_kind":{"listed":{"samples":4,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"4caa20778e7219ba","entry":"compute_volume","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"4caa20778e7219ba"}},{"code_sha256_prefix":"67e14f39a4f3d8e5","entry":"robust_loss","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"67e14f39a4f3d8e5"}},{"code_sha256_prefix":"81c9eec5240c5414","entry":"soft_argmin","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"81c9eec5240c5414"}},{"code_sha256_prefix":"aa666386e35d54a5","entry":"convbn","repo":"meteorshowers/StereoNet","repo_kind":"listed","path":"disparity/models/stereonet_disp.py","file_url":"https://github.com/meteorshowers/StereoNet/blob/HEAD/disparity/models/stereonet_disp.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa666386e35d54a5"}},{"code_sha256_prefix":"873f10dc18effe9c","entry":"convbn_3d","repo":"meteorshowers/StereoNet","repo_kind":"listed","path":"disparity/models/stereonet_disp.py","file_url":"https://github.com/meteorshowers/StereoNet/blob/HEAD/disparity/models/stereonet_disp.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"873f10dc18effe9c"}},{"code_sha256_prefix":"2902bf4410253ff7","entry":"interpolate","repo":"meteorshowers/StereoNet","repo_kind":"listed","path":"disparity/layers/misc.py","file_url":"https://github.com/meteorshowers/StereoNet/blob/HEAD/disparity/layers/misc.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2902bf4410253ff7"}},{"code_sha256_prefix":"7ee1a68e85237f6e","entry":"project_rect_to_image","repo":"meteorshowers/StereoNet","repo_kind":"listed","path":"disparity/models/stereonet.py","file_url":"https://github.com/meteorshowers/StereoNet/blob/HEAD/disparity/models/stereonet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7ee1a68e85237f6e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}