{"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-zero-shot-scale-aware-monocular-depth","title":"Towards Zero-Shot Scale-Aware Monocular Depth Estimation","arxiv_id":"2306.17253","date":"2023-06-29","proceeding":"ICCV 2023 1","authors":["Vitor Guizilini","Igor Vasiljevic","Dian Chen","Rares Ambrus","Adrien Gaidon"],"abstract":"Monocular depth estimation is scale-ambiguous, and thus requires scale supervision to produce metric predictions. Even so, the resulting models will be geometry-specific, with learned scales that cannot be directly transferred across domains. Because of that, recent works focus instead on relative depth, eschewing scale in favor of improved up-to-scale zero-shot transfer. In this work we introduce ZeroDepth, a novel monocular depth estimation framework capable of predicting metric scale for arbitrary test images from different domains and camera parameters. This is achieved by (i) the use of input-level geometric embeddings that enable the network to learn a scale prior over objects; and (ii) decoupling the encoder and decoder stages, via a variational latent representation that is conditioned on single frame information. We evaluated ZeroDepth targeting both outdoor (KITTI, DDAD, nuScenes) and indoor (NYUv2) benchmarks, and achieved a new state-of-the-art in both settings using the same pre-trained model, outperforming methods that train on in-domain data and require test-time scaling to produce metric estimates.","url_abs":"https://arxiv.org/abs/2306.17253v1","url_pdf":"https://arxiv.org/pdf/2306.17253v1.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-zero-shot-scale-aware-monocular-depth","repo_url":"https://github.com/TRI-ML/vidar","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"towards-zero-shot-scale-aware-monocular-depth","repo_url":"https://github.com/cake-lab/Mobile-AR-Depth-Estimation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.17253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.17253"}},"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/cake-lab/Mobile-AR-Depth-Estimation","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TRI-ML/vidar","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":10,"ran_draft_wrong":6,"ran_fixture":2,"unverified":3},"by_repo_kind":{"listed":{"samples":21,"ran":18,"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":21,"samples":[{"code_sha256_prefix":"dcc68d2d5168c6d2","entry":"AttractorLayer","repo":"cake-lab/Mobile-AR-Depth-Estimation","repo_kind":"listed","path":"models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","file_url":"https://github.com/cake-lab/Mobile-AR-Depth-Estimation/blob/HEAD/models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"dcc68d2d5168c6d2"}},{"code_sha256_prefix":"279b5ed1a765f954","entry":"AttractorLayerUnnormed","repo":"cake-lab/Mobile-AR-Depth-Estimation","repo_kind":"listed","path":"models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","file_url":"https://github.com/cake-lab/Mobile-AR-Depth-Estimation/blob/HEAD/models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"279b5ed1a765f954"}},{"code_sha256_prefix":"af08204fe220399a","entry":"ConditionalLogBinomial","repo":"cake-lab/Mobile-AR-Depth-Estimation","repo_kind":"listed","path":"models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","file_url":"https://github.com/cake-lab/Mobile-AR-Depth-Estimation/blob/HEAD/models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"af08204fe220399a"}},{"code_sha256_prefix":"09c47daa6157e163","entry":"DepthModel","repo":"cake-lab/Mobile-AR-Depth-Estimation","repo_kind":"listed","path":"models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","file_url":"https://github.com/cake-lab/Mobile-AR-Depth-Estimation/blob/HEAD/models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"09c47daa6157e163"}},{"code_sha256_prefix":"a6d50c03a384b9f9","entry":"LogBinomial","repo":"cake-lab/Mobile-AR-Depth-Estimation","repo_kind":"listed","path":"models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","file_url":"https://github.com/cake-lab/Mobile-AR-Depth-Estimation/blob/HEAD/models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"a6d50c03a384b9f9"}},{"code_sha256_prefix":"40291ed283381627","entry":"PrepForMidas","repo":"cake-lab/Mobile-AR-Depth-Estimation","repo_kind":"listed","path":"models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","file_url":"https://github.com/cake-lab/Mobile-AR-Depth-Estimation/blob/HEAD/models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"40291ed283381627"}},{"code_sha256_prefix":"c7d5b9ffb26b16f9","entry":"Projector","repo":"cake-lab/Mobile-AR-Depth-Estimation","repo_kind":"listed","path":"models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","file_url":"https://github.com/cake-lab/Mobile-AR-Depth-Estimation/blob/HEAD/models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"c7d5b9ffb26b16f9"}},{"code_sha256_prefix":"02cce835de2b105e","entry":"Resize","repo":"cake-lab/Mobile-AR-Depth-Estimation","repo_kind":"listed","path":"models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","file_url":"https://github.com/cake-lab/Mobile-AR-Depth-Estimation/blob/HEAD/models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"02cce835de2b105e"}},{"code_sha256_prefix":"36f362b347043d76","entry":"SeedBinRegressor","repo":"cake-lab/Mobile-AR-Depth-Estimation","repo_kind":"listed","path":"models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","file_url":"https://github.com/cake-lab/Mobile-AR-Depth-Estimation/blob/HEAD/models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"36f362b347043d76"}},{"code_sha256_prefix":"acc1438609c7087b","entry":"SeedBinRegressorUnnormed","repo":"cake-lab/Mobile-AR-Depth-Estimation","repo_kind":"listed","path":"models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","file_url":"https://github.com/cake-lab/Mobile-AR-Depth-Estimation/blob/HEAD/models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"acc1438609c7087b"}},{"code_sha256_prefix":"0a23d935ca395f43","entry":"denormalize","repo":"cake-lab/Mobile-AR-Depth-Estimation","repo_kind":"listed","path":"models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","file_url":"https://github.com/cake-lab/Mobile-AR-Depth-Estimation/blob/HEAD/models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"0a23d935ca395f43"}},{"code_sha256_prefix":"718d04d747cf4760","entry":"exp_attractor","repo":"cake-lab/Mobile-AR-Depth-Estimation","repo_kind":"listed","path":"models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","file_url":"https://github.com/cake-lab/Mobile-AR-Depth-Estimation/blob/HEAD/models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"718d04d747cf4760"}},{"code_sha256_prefix":"5e36e11ad4768925","entry":"get_activation","repo":"cake-lab/Mobile-AR-Depth-Estimation","repo_kind":"listed","path":"models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","file_url":"https://github.com/cake-lab/Mobile-AR-Depth-Estimation/blob/HEAD/models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"5e36e11ad4768925"}},{"code_sha256_prefix":"4b7edbe448ed6655","entry":"inv_attractor","repo":"cake-lab/Mobile-AR-Depth-Estimation","repo_kind":"listed","path":"models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","file_url":"https://github.com/cake-lab/Mobile-AR-Depth-Estimation/blob/HEAD/models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"4b7edbe448ed6655"}},{"code_sha256_prefix":"98303a9870582d70","entry":"load_state_dict","repo":"cake-lab/Mobile-AR-Depth-Estimation","repo_kind":"listed","path":"models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","file_url":"https://github.com/cake-lab/Mobile-AR-Depth-Estimation/blob/HEAD/models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"98303a9870582d70"}},{"code_sha256_prefix":"fc85e8c7a4e15c37","entry":"load_state_dict_from_url","repo":"cake-lab/Mobile-AR-Depth-Estimation","repo_kind":"listed","path":"models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","file_url":"https://github.com/cake-lab/Mobile-AR-Depth-Estimation/blob/HEAD/models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"fc85e8c7a4e15c37"}},{"code_sha256_prefix":"0da54450ea6be402","entry":"load_wts","repo":"cake-lab/Mobile-AR-Depth-Estimation","repo_kind":"listed","path":"models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","file_url":"https://github.com/cake-lab/Mobile-AR-Depth-Estimation/blob/HEAD/models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"0da54450ea6be402"}},{"code_sha256_prefix":"ace543f1e5d9a720","entry":"log_binom","repo":"cake-lab/Mobile-AR-Depth-Estimation","repo_kind":"listed","path":"models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","file_url":"https://github.com/cake-lab/Mobile-AR-Depth-Estimation/blob/HEAD/models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"ace543f1e5d9a720"}},{"code_sha256_prefix":"1dac62be1b99a756","entry":"MidasCore","repo":"cake-lab/Mobile-AR-Depth-Estimation","repo_kind":"listed","path":"models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","file_url":"https://github.com/cake-lab/Mobile-AR-Depth-Estimation/blob/HEAD/models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"1dac62be1b99a756"}},{"code_sha256_prefix":"26b182be61087f4f","entry":"ZoeDepth","repo":"cake-lab/Mobile-AR-Depth-Estimation","repo_kind":"listed","path":"models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","file_url":"https://github.com/cake-lab/Mobile-AR-Depth-Estimation/blob/HEAD/models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"26b182be61087f4f"}},{"code_sha256_prefix":"a7dc96eec669ee52","entry":"load_state_from_resource","repo":"cake-lab/Mobile-AR-Depth-Estimation","repo_kind":"listed","path":"models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","file_url":"https://github.com/cake-lab/Mobile-AR-Depth-Estimation/blob/HEAD/models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"a7dc96eec669ee52"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}