{"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/focus-on-defocus-bridging-the-synthetic-to","title":"Focus on defocus: bridging the synthetic to real domain gap for depth estimation","arxiv_id":"2005.09623","date":"2020-05-19","proceeding":"CVPR 2020 6","authors":["Maxim Maximov","Kevin Galim","Laura Leal-Taixé"],"abstract":"Data-driven depth estimation methods struggle with the generalization outside their training scenes due to the immense variability of the real-world scenes. This problem can be partially addressed by utilising synthetically generated images, but closing the synthetic-real domain gap is far from trivial. In this paper, we tackle this issue by using domain invariant defocus blur as direct supervision. We leverage defocus cues by using a permutation invariant convolutional neural network that encourages the network to learn from the differences between images with a different point of focus. Our proposed network uses the defocus map as an intermediate supervisory signal. We are able to train our model completely on synthetic data and directly apply it to a wide range of real-world images. We evaluate our model on synthetic and real datasets, showing compelling generalization results and state-of-the-art depth prediction.","url_abs":"https://arxiv.org/abs/2005.09623v1","url_pdf":"https://arxiv.org/pdf/2005.09623v1.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":"focus-on-defocus-bridging-the-synthetic-to","repo_url":"https://github.com/dvl-tum/defocus-net","is_official":1,"mentioned_in_paper":1,"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"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/depth-estimation-on-nyu-depth-v2","task":"Depth Estimation","dataset":"NYU-Depth V2","model":"Defocus/DepthNet (Normalized)","rank_in_archive_order":16,"of":17,"metrics":{"RMSE":"0.013"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2005.09623","atlas_url":"https://app.syntology.ai/?focus=2005.09623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.09623"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/dvl-tum/defocus-net","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"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":0,"samples":[{"code_sha256_prefix":"319e01c0893cd02e","entry":"load_model","repo":"dvl-tum/defocus-net","repo_kind":"official","path":"source/util_func.py","file_url":"https://github.com/dvl-tum/defocus-net/blob/HEAD/source/util_func.py","link_basis":"first_harvest_node","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":"319e01c0893cd02e"}},{"code_sha256_prefix":"2e578908647b4ed5","entry":"read_depth","repo":"dvl-tum/defocus-net","repo_kind":"official","path":"source/file_io.py","file_url":"https://github.com/dvl-tum/defocus-net/blob/HEAD/source/file_io.py","link_basis":"first_harvest_node","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":"2e578908647b4ed5"}},{"code_sha256_prefix":"a73f89c6285332d8","entry":"read_lightfield","repo":"dvl-tum/defocus-net","repo_kind":"official","path":"source/file_io.py","file_url":"https://github.com/dvl-tum/defocus-net/blob/HEAD/source/file_io.py","link_basis":"first_harvest_node","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":"a73f89c6285332d8"}},{"code_sha256_prefix":"92a057d0cd46c847","entry":"read_parameters","repo":"dvl-tum/defocus-net","repo_kind":"official","path":"source/file_io.py","file_url":"https://github.com/dvl-tum/defocus-net/blob/HEAD/source/file_io.py","link_basis":"first_harvest_node","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":"92a057d0cd46c847"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}