{"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/towards-robust-monocular-depth-estimation","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","arxiv_id":"1907.01341","date":"2019-07-02","proceeding":null,"authors":["René Ranftl","Katrin Lasinger","David Hafner","Konrad Schindler","Vladlen Koltun"],"abstract":"The success of monocular depth estimation relies on large and diverse training sets. Due to the challenges associated with acquiring dense ground-truth depth across different environments at scale, a number of datasets with distinct characteristics and biases have emerged. We develop tools that enable mixing multiple datasets during training, even if their annotations are incompatible. In particular, we propose a robust training objective that is invariant to changes in depth range and scale, advocate the use of principled multi-objective learning to combine data from different sources, and highlight the importance of pretraining encoders on auxiliary tasks. Armed with these tools, we experiment with five diverse training datasets, including a new, massive data source: 3D films. To demonstrate the generalization power of our approach we use zero-shot cross-dataset transfer}, i.e. we evaluate on datasets that were not seen during training. The experiments confirm that mixing data from complementary sources greatly improves monocular depth estimation. Our approach clearly outperforms competing methods across diverse datasets, setting a new state of the art for monocular depth estimation. Some results are shown in the supplementary video at https://youtu.be/D46FzVyL9I8","url_abs":"https://arxiv.org/abs/1907.01341v3","url_pdf":"https://arxiv.org/pdf/1907.01341v3.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":"towards-robust-monocular-depth-estimation","repo_url":"https://github.com/intel-isl/MiDaS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"towards-robust-monocular-depth-estimation","repo_url":"https://github.com/AbirKhan96/Intel-ISL-MiDaS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"towards-robust-monocular-depth-estimation","repo_url":"https://github.com/JeffreyMagee/Distance-measure-based-on-depth-estimation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"towards-robust-monocular-depth-estimation","repo_url":"https://github.com/Mind23-2/MindCode-57","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"towards-robust-monocular-depth-estimation","repo_url":"https://github.com/ahmedmostafa0x61/Depth_Estimation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"towards-robust-monocular-depth-estimation","repo_url":"https://github.com/alexeyab/midas","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"towards-robust-monocular-depth-estimation","repo_url":"https://github.com/anlok/depthmap-loktev","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"towards-robust-monocular-depth-estimation","repo_url":"https://github.com/freshtan/midas_v2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"towards-robust-monocular-depth-estimation","repo_url":"https://github.com/isl-org/MiDaS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"towards-robust-monocular-depth-estimation","repo_url":"https://github.com/lasinger/3DVideos2Stereo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"towards-robust-monocular-depth-estimation","repo_url":"https://github.com/picsart-ai-research/text2video-zero","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"towards-robust-monocular-depth-estimation","repo_url":"https://github.com/prakashSidd18/blind_augmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"towards-robust-monocular-depth-estimation","repo_url":"https://github.com/scut-math-srp/Distance-measure-based-on-depth-estimation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"towards-robust-monocular-depth-estimation","repo_url":"https://github.com/shubham0204/Realtime_MiDaS_Depth_Estimation_Android","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"towards-robust-monocular-depth-estimation","repo_url":"https://github.com/vishal-kataria/MiDaS-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"towards-robust-monocular-depth-estimation","repo_url":"https://github.com/mindspore-ai/models/tree/master/research/cv/midas","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/depth-estimation-on-dcm","task":"Depth Estimation","dataset":"DCM","model":"MIDAS","rank_in_archive_order":2,"of":3,"metrics":{"Abs Rel":"0.309","RMSE":"1.033","RMSE log":"0.375","Sq Rel":"0.381"},"uses_additional_data":false},{"leaderboard":"/sota/depth-estimation-on-ebdtheque","task":"Depth Estimation","dataset":"eBDtheque","model":"MIDAS","rank_in_archive_order":2,"of":3,"metrics":{"Abs Rel":"0.419","RMSE":"1.416","RMSE log":"0.659","Sq Rel":"0.503"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-eth3d","task":"Monocular Depth Estimation","dataset":"ETH3D","model":"MiDaS","rank_in_archive_order":10,"of":10,"metrics":{"Delta < 1.25":"0.0752","absolute relative error":"0.0184"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1907.01341","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.01341"}},"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/shubham0204/Realtime_MiDaS_Depth_Estimation_Android","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/isl-org/MiDaS","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/scut-math-srp/Distance-measure-based-on-depth-estimation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alexeyab/midas","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AbirKhan96/Intel-ISL-MiDaS","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vishal-kataria/MiDaS-master","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/freshtan/midas_v2","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JeffreyMagee/Distance-measure-based-on-depth-estimation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lasinger/3DVideos2Stereo","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/prakashSidd18/blind_augmentation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/anlok/depthmap-loktev","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/intel-isl/MiDaS","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ahmedmostafa0x61/Depth_Estimation","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Mind23-2/MindCode-57","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/picsart-ai-research/text2video-zero","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindspore-ai/models/tree/master/research/cv/midas","reach":null}],"summary":{"ran":4,"ran_draft_wrong":2,"unverified":11},"by_repo_kind":{"listed":{"samples":17,"ran":6,"repositories":4}},"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":"8d4e5ab503856d09","entry":"apply_min_size","repo":"anlok/depthmap-loktev","repo_kind":"listed","path":"models/transforms.py","file_url":"https://github.com/anlok/depthmap-loktev/blob/HEAD/models/transforms.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8d4e5ab503856d09"}},{"code_sha256_prefix":"b9e24c3e3e0e88a7","entry":"merge","repo":"freshtan/midas_v2","repo_kind":"listed","path":"src/config.py","file_url":"https://github.com/freshtan/midas_v2/blob/HEAD/src/config.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b9e24c3e3e0e88a7"}},{"code_sha256_prefix":"a3b0b33caf369c41","entry":"patch_embed_forward","repo":"isl-org/MiDaS","repo_kind":"listed","path":"midas/backbones/beit.py","file_url":"https://github.com/isl-org/MiDaS/blob/HEAD/midas/backbones/beit.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a3b0b33caf369c41"}},{"code_sha256_prefix":"fa28021adde0f186","entry":"read_image","repo":"anlok/depthmap-loktev","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/anlok/depthmap-loktev/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fa28021adde0f186"}},{"code_sha256_prefix":"188a19865f88f383","entry":"read_pfm","repo":"anlok/depthmap-loktev","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/anlok/depthmap-loktev/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"188a19865f88f383"}},{"code_sha256_prefix":"80ea105639cd9efd","entry":"resize_image","repo":"anlok/depthmap-loktev","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/anlok/depthmap-loktev/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"80ea105639cd9efd"}},{"code_sha256_prefix":"c0f7dd2e78f91f10","entry":"associate","repo":"freshtan/midas_v2","repo_kind":"listed","path":"preprocess/associate.py","file_url":"https://github.com/freshtan/midas_v2/blob/HEAD/preprocess/associate.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":"c0f7dd2e78f91f10"}},{"code_sha256_prefix":"cc0b35f6d7118df1","entry":"attention_forward","repo":"isl-org/MiDaS","repo_kind":"listed","path":"midas/backbones/beit.py","file_url":"https://github.com/isl-org/MiDaS/blob/HEAD/midas/backbones/beit.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":"cc0b35f6d7118df1"}},{"code_sha256_prefix":"98b6d75cef37e16d","entry":"depth_read_kitti","repo":"freshtan/midas_v2","repo_kind":"listed","path":"src/util.py","file_url":"https://github.com/freshtan/midas_v2/blob/HEAD/src/util.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":"98b6d75cef37e16d"}},{"code_sha256_prefix":"62d386dcfc041ca8","entry":"forward_beit","repo":"isl-org/MiDaS","repo_kind":"listed","path":"midas/backbones/beit.py","file_url":"https://github.com/isl-org/MiDaS/blob/HEAD/midas/backbones/beit.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":"62d386dcfc041ca8"}},{"code_sha256_prefix":"c3d82023511f51f2","entry":"get_eval_result","repo":"freshtan/midas_v2","repo_kind":"listed","path":"postprocess.py","file_url":"https://github.com/freshtan/midas_v2/blob/HEAD/postprocess.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":"c3d82023511f51f2"}},{"code_sha256_prefix":"738456e1b7388e7e","entry":"parse_cli_to_yaml","repo":"freshtan/midas_v2","repo_kind":"listed","path":"src/config.py","file_url":"https://github.com/freshtan/midas_v2/blob/HEAD/src/config.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":"738456e1b7388e7e"}},{"code_sha256_prefix":"96a9939953d5992d","entry":"parse_yaml","repo":"freshtan/midas_v2","repo_kind":"listed","path":"src/config.py","file_url":"https://github.com/freshtan/midas_v2/blob/HEAD/src/config.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":"96a9939953d5992d"}},{"code_sha256_prefix":"079a28e19eb8f028","entry":"processShotFile","repo":"lasinger/3DVideos2Stereo","repo_kind":"listed","path":"genTraining_recurr.py","file_url":"https://github.com/lasinger/3DVideos2Stereo/blob/HEAD/genTraining_recurr.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":"079a28e19eb8f028"}},{"code_sha256_prefix":"780a0dcc75fb0c82","entry":"read_file_list","repo":"freshtan/midas_v2","repo_kind":"listed","path":"preprocess/associate.py","file_url":"https://github.com/freshtan/midas_v2/blob/HEAD/preprocess/associate.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":"780a0dcc75fb0c82"}},{"code_sha256_prefix":"484108557b544812","entry":"read_flow","repo":"lasinger/3DVideos2Stereo","repo_kind":"listed","path":"get_disp_and_uncertainty.py","file_url":"https://github.com/lasinger/3DVideos2Stereo/blob/HEAD/get_disp_and_uncertainty.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":"484108557b544812"}},{"code_sha256_prefix":"d0f2d7d797bf8806","entry":"write_depth","repo":"freshtan/midas_v2","repo_kind":"listed","path":"src/util.py","file_url":"https://github.com/freshtan/midas_v2/blob/HEAD/src/util.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":"d0f2d7d797bf8806"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}