{"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/depth-anything-unleashing-the-power-of-large","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","arxiv_id":"2401.10891","date":"2024-01-19","proceeding":"CVPR 2024 1","authors":["Lihe Yang","Bingyi Kang","Zilong Huang","Xiaogang Xu","Jiashi Feng","Hengshuang Zhao"],"abstract":"This work presents Depth Anything, a highly practical solution for robust monocular depth estimation. Without pursuing novel technical modules, we aim to build a simple yet powerful foundation model dealing with any images under any circumstances. To this end, we scale up the dataset by designing a data engine to collect and automatically annotate large-scale unlabeled data (~62M), which significantly enlarges the data coverage and thus is able to reduce the generalization error. We investigate two simple yet effective strategies that make data scaling-up promising. First, a more challenging optimization target is created by leveraging data augmentation tools. It compels the model to actively seek extra visual knowledge and acquire robust representations. Second, an auxiliary supervision is developed to enforce the model to inherit rich semantic priors from pre-trained encoders. We evaluate its zero-shot capabilities extensively, including six public datasets and randomly captured photos. It demonstrates impressive generalization ability. Further, through fine-tuning it with metric depth information from NYUv2 and KITTI, new SOTAs are set. Our better depth model also results in a better depth-conditioned ControlNet. Our models are released at https://github.com/LiheYoung/Depth-Anything.","url_abs":"https://arxiv.org/abs/2401.10891v2","url_pdf":"https://arxiv.org/pdf/2401.10891v2.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":"depth-anything-unleashing-the-power-of-large","repo_url":"https://github.com/LiheYoung/Depth-Anything","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"depth-anything-unleashing-the-power-of-large","repo_url":"https://github.com/JTRNEO/SynRS3D","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"depth-anything-unleashing-the-power-of-large","repo_url":"https://github.com/duan-song/SATNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"depth-anything-unleashing-the-power-of-large","repo_url":"https://github.com/fabio-sim/Depth-Anything-ONNX","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"depth-anything-unleashing-the-power-of-large","repo_url":"https://github.com/greatenanoymous/monodpt_grasp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"depth-anything-unleashing-the-power-of-large","repo_url":"https://github.com/MindCode-4/code-3/tree/main/depth_anything","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"depth-anything-unleashing-the-power-of-large","repo_url":"https://github.com/spacewalk01/depth-anything-tensorrt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/monocular-depth-estimation-on-eth3d","task":"Monocular Depth Estimation","dataset":"ETH3D","model":"Depth Anything","rank_in_archive_order":4,"of":10,"metrics":{"Delta < 1.25":"0.882","absolute relative error":"0.0127"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split","model":"Depth Anything","rank_in_archive_order":10,"of":79,"metrics":{"Delta < 1.25":"0.982","Delta < 1.25^2":"0.998","Delta < 1.25^3":"1.000","RMSE":"1.896","RMSE log":"0.069","Sq Rel":"0.121","absolute relative error":"0.046"},"uses_additional_data":true},{"leaderboard":"/sota/monocular-depth-estimation-on-nyu-depth-v2","task":"Monocular Depth Estimation","dataset":"NYU-Depth V2","model":"Depth Anything","rank_in_archive_order":11,"of":85,"metrics":{"Delta < 1.25":"0.984","Delta < 1.25^2":"0.998","Delta < 1.25^3":"1.000","RMSE":"0.206","absolute relative error":"0.056","log 10":"0.024"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset":"Cityscapes test","model":"Depth Anything","rank_in_archive_order":8,"of":105,"metrics":{"Mean IoU (class)":"84.8%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes-val","task":"Semantic Segmentation","dataset":"Cityscapes val","model":"Depth Anything","rank_in_archive_order":8,"of":99,"metrics":{"mIoU":"86.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.10891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10891"}},"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/JTRNEO/SynRS3D","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/duan-song/SATNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/spacewalk01/depth-anything-tensorrt","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindCode-4/code-3/tree/main/depth_anything","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fabio-sim/Depth-Anything-ONNX","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/greatenanoymous/monodpt_grasp","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LiheYoung/Depth-Anything","reach":null}],"summary":{"ran":1,"ran_draft_wrong":1,"ran_fixture":1,"unverified":8},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":10,"ran":2,"repositories":2}},"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":"spacewalk01/depth-anything-tensorrt","repo_kind":"listed","path":"python/depth_anything/util/transform.py","file_url":"https://github.com/spacewalk01/depth-anything-tensorrt/blob/HEAD/python/depth_anything/util/transform.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":"8ffddb7d6410c4f1","entry":"infer","repo":"greatenanoymous/monodpt_grasp","repo_kind":"listed","path":"metric_depth/evaluate.py","file_url":"https://github.com/greatenanoymous/monodpt_grasp/blob/HEAD/metric_depth/evaluate.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8ffddb7d6410c4f1"}},{"code_sha256_prefix":"6ff08048a8305588","entry":"load_ckpt","repo":"LiheYoung/Depth-Anything","repo_kind":"official","path":"metric_depth/train_mono.py","file_url":"https://github.com/LiheYoung/Depth-Anything/blob/HEAD/metric_depth/train_mono.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6ff08048a8305588"}},{"code_sha256_prefix":"8f37f1dad72ee59a","entry":"depth2PointCloud","repo":"greatenanoymous/monodpt_grasp","repo_kind":"listed","path":"metric_depth/create_pc.py","file_url":"https://github.com/greatenanoymous/monodpt_grasp/blob/HEAD/metric_depth/create_pc.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":"8f37f1dad72ee59a"}},{"code_sha256_prefix":"0813761694382465","entry":"depth2PointCloudFakeDepth","repo":"greatenanoymous/monodpt_grasp","repo_kind":"listed","path":"metric_depth/create_pc.py","file_url":"https://github.com/greatenanoymous/monodpt_grasp/blob/HEAD/metric_depth/create_pc.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":"0813761694382465"}},{"code_sha256_prefix":"03b9e7ce46a39fe4","entry":"infer_complete_depth","repo":"greatenanoymous/monodpt_grasp","repo_kind":"listed","path":"metric_depth/evaluate_complete.py","file_url":"https://github.com/greatenanoymous/monodpt_grasp/blob/HEAD/metric_depth/evaluate_complete.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":"03b9e7ce46a39fe4"}},{"code_sha256_prefix":"c7ed25a9b6ac1ab2","entry":"infer_relative_depth","repo":"greatenanoymous/monodpt_grasp","repo_kind":"listed","path":"metric_depth/evaluate_relative.py","file_url":"https://github.com/greatenanoymous/monodpt_grasp/blob/HEAD/metric_depth/evaluate_relative.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":"c7ed25a9b6ac1ab2"}},{"code_sha256_prefix":"24a768b877a487a4","entry":"load_image","repo":"spacewalk01/depth-anything-tensorrt","repo_kind":"listed","path":"python/depth_anything/util/transform.py","file_url":"https://github.com/spacewalk01/depth-anything-tensorrt/blob/HEAD/python/depth_anything/util/transform.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":"24a768b877a487a4"}},{"code_sha256_prefix":"fe823f83592f9fc3","entry":"project_point","repo":"greatenanoymous/monodpt_grasp","repo_kind":"listed","path":"metric_depth/camera.py","file_url":"https://github.com/greatenanoymous/monodpt_grasp/blob/HEAD/metric_depth/camera.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":"fe823f83592f9fc3"}},{"code_sha256_prefix":"822210307d6c6191","entry":"project_point_to_pixel","repo":"greatenanoymous/monodpt_grasp","repo_kind":"listed","path":"metric_depth/camera.py","file_url":"https://github.com/greatenanoymous/monodpt_grasp/blob/HEAD/metric_depth/camera.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":"822210307d6c6191"}},{"code_sha256_prefix":"55658559d5046929","entry":"reprojection_error2d","repo":"greatenanoymous/monodpt_grasp","repo_kind":"listed","path":"metric_depth/camera.py","file_url":"https://github.com/greatenanoymous/monodpt_grasp/blob/HEAD/metric_depth/camera.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":"55658559d5046929"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}