{"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-to-adapt-for-stereo","title":"Learning to Adapt for Stereo","arxiv_id":"1904.02957","date":"2019-04-05","proceeding":"CVPR 2019 6","authors":["Alessio Tonioni","Oscar Rahnama","Thomas Joy","Luigi Di Stefano","Thalaiyasingam Ajanthan","Philip H. S. Torr"],"abstract":"Real world applications of stereo depth estimation require models that are\nrobust to dynamic variations in the environment. Even though deep learning\nbased stereo methods are successful, they often fail to generalize to unseen\nvariations in the environment, making them less suitable for practical\napplications such as autonomous driving. In this work, we introduce a\n\"learning-to-adapt\" framework that enables deep stereo methods to continuously\nadapt to new target domains in an unsupervised manner. Specifically, our\napproach incorporates the adaptation procedure into the learning objective to\nobtain a base set of parameters that are better suited for unsupervised online\nadaptation. To further improve the quality of the adaptation, we learn a\nconfidence measure that effectively masks the errors introduced during the\nunsupervised adaptation. We evaluate our method on synthetic and real-world\nstereo datasets and our experiments evidence that learning-to-adapt is, indeed\nbeneficial for online adaptation on vastly different domains.","url_abs":"http://arxiv.org/abs/1904.02957v1","url_pdf":"http://arxiv.org/pdf/1904.02957v1.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-to-adapt-for-stereo","repo_url":"https://github.com/CVLAB-Unibo/Learning2AdaptForStereo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"stereo-depth-estimation","task_name":"Stereo Depth Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.02957","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.02957"}},"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/CVLAB-Unibo/Learning2AdaptForStereo","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_violates":1,"ran_draft_wrong":1,"unverified":18},"by_repo_kind":{"official":{"samples":20,"ran":2,"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":0,"samples":[{"code_sha256_prefix":"59c0d53cfcbb2398","entry":"average_vars","repo":"CVLAB-Unibo/Learning2AdaptForStereo","repo_kind":"official","path":"Data_utils/variables.py","file_url":"https://github.com/CVLAB-Unibo/Learning2AdaptForStereo/blob/HEAD/Data_utils/variables.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"59c0d53cfcbb2398"}},{"code_sha256_prefix":"3880e32be4fd7c7f","entry":"subtract_vars","repo":"CVLAB-Unibo/Learning2AdaptForStereo","repo_kind":"official","path":"Data_utils/variables.py","file_url":"https://github.com/CVLAB-Unibo/Learning2AdaptForStereo/blob/HEAD/Data_utils/variables.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3880e32be4fd7c7f"}},{"code_sha256_prefix":"27cc437d9adfb80e","entry":"augment","repo":"CVLAB-Unibo/Learning2AdaptForStereo","repo_kind":"official","path":"Data_utils/preprocessing.py","file_url":"https://github.com/CVLAB-Unibo/Learning2AdaptForStereo/blob/HEAD/Data_utils/preprocessing.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"27cc437d9adfb80e"}},{"code_sha256_prefix":"ad1b44ffe682391b","entry":"batch_norm","repo":"CVLAB-Unibo/Learning2AdaptForStereo","repo_kind":"official","path":"Nets/sharedLayers.py","file_url":"https://github.com/CVLAB-Unibo/Learning2AdaptForStereo/blob/HEAD/Nets/sharedLayers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ad1b44ffe682391b"}},{"code_sha256_prefix":"7a696b37d539597b","entry":"checkExistance","repo":"CVLAB-Unibo/Learning2AdaptForStereo","repo_kind":"official","path":"Nets/factory.py","file_url":"https://github.com/CVLAB-Unibo/Learning2AdaptForStereo/blob/HEAD/Nets/factory.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7a696b37d539597b"}},{"code_sha256_prefix":"73c89e4ebc93f573","entry":"check_for_weights_or_restore_them","repo":"CVLAB-Unibo/Learning2AdaptForStereo","repo_kind":"official","path":"Data_utils/weights_utils.py","file_url":"https://github.com/CVLAB-Unibo/Learning2AdaptForStereo/blob/HEAD/Data_utils/weights_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"73c89e4ebc93f573"}},{"code_sha256_prefix":"a605840e0a151022","entry":"correlation","repo":"CVLAB-Unibo/Learning2AdaptForStereo","repo_kind":"official","path":"Nets/sharedLayers.py","file_url":"https://github.com/CVLAB-Unibo/Learning2AdaptForStereo/blob/HEAD/Nets/sharedLayers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a605840e0a151022"}},{"code_sha256_prefix":"1b3c3db337ba04f1","entry":"getStereoNet","repo":"CVLAB-Unibo/Learning2AdaptForStereo","repo_kind":"official","path":"Nets/factory.py","file_url":"https://github.com/CVLAB-Unibo/Learning2AdaptForStereo/blob/HEAD/Nets/factory.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1b3c3db337ba04f1"}},{"code_sha256_prefix":"e72daa74fbf6cb2c","entry":"get_meta_learner","repo":"CVLAB-Unibo/Learning2AdaptForStereo","repo_kind":"official","path":"MetaTrainer/factory.py","file_url":"https://github.com/CVLAB-Unibo/Learning2AdaptForStereo/blob/HEAD/MetaTrainer/factory.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e72daa74fbf6cb2c"}},{"code_sha256_prefix":"52ac8b9a9d55427b","entry":"get_var_to_restore_list","repo":"CVLAB-Unibo/Learning2AdaptForStereo","repo_kind":"official","path":"Data_utils/weights_utils.py","file_url":"https://github.com/CVLAB-Unibo/Learning2AdaptForStereo/blob/HEAD/Data_utils/weights_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"52ac8b9a9d55427b"}},{"code_sha256_prefix":"945ad47f08483c8b","entry":"get_variable","repo":"CVLAB-Unibo/Learning2AdaptForStereo","repo_kind":"official","path":"Nets/sharedLayers.py","file_url":"https://github.com/CVLAB-Unibo/Learning2AdaptForStereo/blob/HEAD/Nets/sharedLayers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"945ad47f08483c8b"}},{"code_sha256_prefix":"382960e74b17b40a","entry":"interpolate_vars","repo":"CVLAB-Unibo/Learning2AdaptForStereo","repo_kind":"official","path":"Data_utils/variables.py","file_url":"https://github.com/CVLAB-Unibo/Learning2AdaptForStereo/blob/HEAD/Data_utils/variables.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"382960e74b17b40a"}},{"code_sha256_prefix":"f7bd997c454b72ef","entry":"l1","repo":"CVLAB-Unibo/Learning2AdaptForStereo","repo_kind":"official","path":"Losses/loss_factory.py","file_url":"https://github.com/CVLAB-Unibo/Learning2AdaptForStereo/blob/HEAD/Losses/loss_factory.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f7bd997c454b72ef"}},{"code_sha256_prefix":"554090648d5d1688","entry":"l2","repo":"CVLAB-Unibo/Learning2AdaptForStereo","repo_kind":"official","path":"Losses/loss_factory.py","file_url":"https://github.com/CVLAB-Unibo/Learning2AdaptForStereo/blob/HEAD/Losses/loss_factory.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"554090648d5d1688"}},{"code_sha256_prefix":"741b7a75bf889cab","entry":"mean_l1","repo":"CVLAB-Unibo/Learning2AdaptForStereo","repo_kind":"official","path":"Losses/loss_factory.py","file_url":"https://github.com/CVLAB-Unibo/Learning2AdaptForStereo/blob/HEAD/Losses/loss_factory.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"741b7a75bf889cab"}},{"code_sha256_prefix":"683bb31446329db4","entry":"pad_image","repo":"CVLAB-Unibo/Learning2AdaptForStereo","repo_kind":"official","path":"Data_utils/preprocessing.py","file_url":"https://github.com/CVLAB-Unibo/Learning2AdaptForStereo/blob/HEAD/Data_utils/preprocessing.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"683bb31446329db4"}},{"code_sha256_prefix":"717593d2efab32b0","entry":"random_crop","repo":"CVLAB-Unibo/Learning2AdaptForStereo","repo_kind":"official","path":"Data_utils/preprocessing.py","file_url":"https://github.com/CVLAB-Unibo/Learning2AdaptForStereo/blob/HEAD/Data_utils/preprocessing.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"717593d2efab32b0"}},{"code_sha256_prefix":"5bd87bf6c7536635","entry":"readPFM","repo":"CVLAB-Unibo/Learning2AdaptForStereo","repo_kind":"official","path":"Data_utils/data_reader.py","file_url":"https://github.com/CVLAB-Unibo/Learning2AdaptForStereo/blob/HEAD/Data_utils/data_reader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5bd87bf6c7536635"}},{"code_sha256_prefix":"dd9ab5ac64bbf156","entry":"read_image_from_disc","repo":"CVLAB-Unibo/Learning2AdaptForStereo","repo_kind":"official","path":"Data_utils/data_reader.py","file_url":"https://github.com/CVLAB-Unibo/Learning2AdaptForStereo/blob/HEAD/Data_utils/data_reader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dd9ab5ac64bbf156"}},{"code_sha256_prefix":"bd701eec441ee4e5","entry":"read_list_file","repo":"CVLAB-Unibo/Learning2AdaptForStereo","repo_kind":"official","path":"Data_utils/data_reader.py","file_url":"https://github.com/CVLAB-Unibo/Learning2AdaptForStereo/blob/HEAD/Data_utils/data_reader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bd701eec441ee4e5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}