{"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/metric3d-v2-a-versatile-monocular-geometric-1","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","arxiv_id":"2404.15506","date":"2024-03-22","proceeding":"Under review for Transaction 2024 4","authors":["Mu Hu","Wei Yin","Chi Zhang","Zhipeng Cai","Xiaoxiao Long","Kaixuan Wang","Hao Chen","Gang Yu","Chunhua Shen","Shaojie Shen"],"abstract":"We introduce Metric3D v2, a geometric foundation model for zero-shot metric depth and surface normal estimation from a single image, which is crucial for metric 3D recovery. While depth and normal are geometrically related and highly complimentary, they present distinct challenges. SoTA monocular depth methods achieve zero-shot generalization by learning affine-invariant depths, which cannot recover real-world metrics. Meanwhile, SoTA normal estimation methods have limited zero-shot performance due to the lack of large-scale labeled data. To tackle these issues, we propose solutions for both metric depth estimation and surface normal estimation. For metric depth estimation, we show that the key to a zero-shot single-view model lies in resolving the metric ambiguity from various camera models and large-scale data training. We propose a canonical camera space transformation module, which explicitly addresses the ambiguity problem and can be effortlessly plugged into existing monocular models. For surface normal estimation, we propose a joint depth-normal optimization module to distill diverse data knowledge from metric depth, enabling normal estimators to learn beyond normal labels. Equipped with these modules, our depth-normal models can be stably trained with over 16 million of images from thousands of camera models with different-type annotations, resulting in zero-shot generalization to in-the-wild images with unseen camera settings. Our method enables the accurate recovery of metric 3D structures on randomly collected internet images, paving the way for plausible single-image metrology. Our project page is at https://JUGGHM.github.io/Metric3Dv2.","url_abs":"https://arxiv.org/abs/2404.15506v4","url_pdf":"https://arxiv.org/pdf/2404.15506v4.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":"metric3d-v2-a-versatile-monocular-geometric-1","repo_url":"https://github.com/yvanyin/metric3d","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"surface-normal-estimation","task_name":"Surface Normal Estimation"},{"task_slug":"zero-shot-generalization","task_name":"Zero-shot Generalization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/monocular-depth-estimation-on-ibims-1","task":"Monocular Depth Estimation","dataset":"IBims-1","model":"Metric3D-v2(L, ZS)","rank_in_archive_order":4,"of":4,"metrics":{"δ1.25":"0.969"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-kitti-eigen","task":"Monocular Depth Estimation","dataset":"KITTI Eigen split","model":"Metric3Dv2 (g2, FT, 80m, flip_aug_test)","rank_in_archive_order":4,"of":79,"metrics":{"Delta < 1.25":"0.989","Delta < 1.25^2":"0.998","Delta < 1.25^3":"1.000","RMSE":"1.766","RMSE log":"0.060","absolute relative error":"0.039"},"uses_additional_data":true},{"leaderboard":"/sota/monocular-depth-estimation-on-nyu-depth-v2","task":"Monocular Depth Estimation","dataset":"NYU-Depth V2","model":"Metric3Dv2(L, FT)","rank_in_archive_order":6,"of":85,"metrics":{"Delta < 1.25":"0.989","Delta < 1.25^2":"0.998","Delta < 1.25^3":"1.000","RMSE":"0.183","absolute relative error":"0.047","log 10":"0.020"},"uses_additional_data":true},{"leaderboard":"/sota/surface-normals-estimation-on-ibims-1","task":"Surface Normals Estimation","dataset":"IBims-1","model":"Metric3Dv2(g2, ZS)","rank_in_archive_order":2,"of":2,"metrics":{"% < 11.25":"69.7","% < 22.5":"76.2","% < 30":"78.8","Mean":"19.6"},"uses_additional_data":true},{"leaderboard":"/sota/surface-normals-estimation-on-nyu-depth-v2-1","task":"Surface Normals Estimation","dataset":"NYU Depth v2","model":"Metric3Dv2(L, FT)","rank_in_archive_order":1,"of":6,"metrics":{"% < 11.25":"68.8","% < 22.5":"84.9","% < 30":"89.8","Mean Angle Error":"12.0","RMSE":"19.2"},"uses_additional_data":true},{"leaderboard":"/sota/surface-normals-estimation-on-scannetv2","task":"Surface Normals Estimation","dataset":"ScanNetV2","model":"Metric3Dv2 (g2, In-domain)","rank_in_archive_order":1,"of":3,"metrics":{"% < 11.25":"77.8","% < 22.5":"90.1","% < 30":"93.5","Mean Angle Error":"9.2"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.15506","atlas_url":"https://app.syntology.ai/?focus=2404.15506","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15506"}},"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/yvanyin/metric3d","reach":null}],"summary":{"ran_fixture":2,"ran_honours":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"71b3e03a56d81aec","entry":"drop_add_residual_stochastic_depth","repo":"yvanyin/metric3d","repo_kind":"official","path":"mono/model/backbones/ViT_DINO.py","file_url":"https://github.com/yvanyin/metric3d/blob/HEAD/mono/model/backbones/ViT_DINO.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"71b3e03a56d81aec"}},{"code_sha256_prefix":"c157f5b112b3a392","entry":"drop_path","repo":"yvanyin/metric3d","repo_kind":"official","path":"mono/model/backbones/ViT_DINO.py","file_url":"https://github.com/yvanyin/metric3d/blob/HEAD/mono/model/backbones/ViT_DINO.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"c157f5b112b3a392"}},{"code_sha256_prefix":"3c04490a215299f2","entry":"make_2tuple","repo":"yvanyin/metric3d","repo_kind":"official","path":"mono/model/backbones/ViT_DINO.py","file_url":"https://github.com/yvanyin/metric3d/blob/HEAD/mono/model/backbones/ViT_DINO.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"3c04490a215299f2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}