{"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/zoedepth-zero-shot-transfer-by-combining","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","arxiv_id":"2302.12288","date":"2023-02-23","proceeding":null,"authors":["Shariq Farooq Bhat","Reiner Birkl","Diana Wofk","Peter Wonka","Matthias Müller"],"abstract":"This paper tackles the problem of depth estimation from a single image. Existing work either focuses on generalization performance disregarding metric scale, i.e. relative depth estimation, or state-of-the-art results on specific datasets, i.e. metric depth estimation. We propose the first approach that combines both worlds, leading to a model with excellent generalization performance while maintaining metric scale. Our flagship model, ZoeD-M12-NK, is pre-trained on 12 datasets using relative depth and fine-tuned on two datasets using metric depth. We use a lightweight head with a novel bin adjustment design called metric bins module for each domain. During inference, each input image is automatically routed to the appropriate head using a latent classifier. Our framework admits multiple configurations depending on the datasets used for relative depth pre-training and metric fine-tuning. Without pre-training, we can already significantly improve the state of the art (SOTA) on the NYU Depth v2 indoor dataset. Pre-training on twelve datasets and fine-tuning on the NYU Depth v2 indoor dataset, we can further improve SOTA for a total of 21% in terms of relative absolute error (REL). Finally, ZoeD-M12-NK is the first model that can jointly train on multiple datasets (NYU Depth v2 and KITTI) without a significant drop in performance and achieve unprecedented zero-shot generalization performance to eight unseen datasets from both indoor and outdoor domains. The code and pre-trained models are publicly available at https://github.com/isl-org/ZoeDepth .","url_abs":"https://arxiv.org/abs/2302.12288v1","url_pdf":"https://arxiv.org/pdf/2302.12288v1.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":"zoedepth-zero-shot-transfer-by-combining","repo_url":"https://github.com/isl-org/ZoeDepth","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"zoedepth-zero-shot-transfer-by-combining","repo_url":"https://github.com/GuidoManni/BodySLAM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"zoedepth-zero-shot-transfer-by-combining","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},{"paper_slug":"zoedepth-zero-shot-transfer-by-combining","repo_url":"https://github.com/intel-isl/MiDaS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"zoedepth-zero-shot-transfer-by-combining","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":"zoedepth-zero-shot-transfer-by-combining","repo_url":"https://github.com/thygate/stable-diffusion-webui-depthmap-script","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"},{"task_slug":"zero-shot-generalization","task_name":"Zero-shot Generalization"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"adaptivebins","method_name":"AdaptiveBins"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/monocular-depth-estimation-on-nyu-depth-v2","task":"Monocular Depth Estimation","dataset":"NYU-Depth V2","model":"ZoeD-M12-N","rank_in_archive_order":26,"of":85,"metrics":{"Delta < 1.25":"0.955","Delta < 1.25^2":"0.995","Delta < 1.25^3":"0.999","RMSE":"0.270","absolute relative error":"0.075","log 10":"0.032"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2302.12288","atlas_url":"https://app.syntology.ai/?focus=2302.12288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.12288"}},"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/isl-org/MiDaS","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/GuidoManni/BodySLAM","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thygate/stable-diffusion-webui-depthmap-script","reach":{"status":"ok","spdx":"MIT"}},{"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/isl-org/ZoeDepth","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/intel-isl/MiDaS","reach":null}],"summary":{"ran_draft_wrong":6,"ran":5,"ran_fixture":1,"unverified":4},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":14,"ran":10,"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":1,"samples":[{"code_sha256_prefix":"d9def42110729a85","entry":"conv1x1","repo":"thygate/stable-diffusion-webui-depthmap-script","repo_kind":"listed","path":"lib/Resnext_torch.py","file_url":"https://github.com/thygate/stable-diffusion-webui-depthmap-script/blob/HEAD/lib/Resnext_torch.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d9def42110729a85"}},{"code_sha256_prefix":"160bb14bd76201b4","entry":"conv3x3","repo":"thygate/stable-diffusion-webui-depthmap-script","repo_kind":"listed","path":"lib/Resnext_torch.py","file_url":"https://github.com/thygate/stable-diffusion-webui-depthmap-script/blob/HEAD/lib/Resnext_torch.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"160bb14bd76201b4"}},{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"thygate/stable-diffusion-webui-depthmap-script","repo_kind":"listed","path":"lib/Resnet.py","file_url":"https://github.com/thygate/stable-diffusion-webui-depthmap-script/blob/HEAD/lib/Resnet.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"13416aca1c543254","entry":"estimatezoedepth","repo":"thygate/stable-diffusion-webui-depthmap-script","repo_kind":"listed","path":"src/depthmap_generation.py","file_url":"https://github.com/thygate/stable-diffusion-webui-depthmap-script/blob/HEAD/src/depthmap_generation.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":"13416aca1c543254"}},{"code_sha256_prefix":"a467686f61537560","entry":"get_installed_version","repo":"thygate/stable-diffusion-webui-depthmap-script","repo_kind":"listed","path":"install.py","file_url":"https://github.com/thygate/stable-diffusion-webui-depthmap-script/blob/HEAD/install.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a467686f61537560"}},{"code_sha256_prefix":"8ffddb7d6410c4f1","entry":"infer","repo":"isl-org/ZoeDepth","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/isl-org/ZoeDepth/blob/HEAD/evaluate.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":"8ffddb7d6410c4f1"}},{"code_sha256_prefix":"6ff08048a8305588","entry":"load_ckpt","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"6ff08048a8305588"}},{"code_sha256_prefix":"42823db097a59e8e","entry":"resnet18","repo":"thygate/stable-diffusion-webui-depthmap-script","repo_kind":"listed","path":"lib/Resnet.py","file_url":"https://github.com/thygate/stable-diffusion-webui-depthmap-script/blob/HEAD/lib/Resnet.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":"42823db097a59e8e"}},{"code_sha256_prefix":"39037cdb0fe985b1","entry":"resnet34","repo":"thygate/stable-diffusion-webui-depthmap-script","repo_kind":"listed","path":"lib/Resnet.py","file_url":"https://github.com/thygate/stable-diffusion-webui-depthmap-script/blob/HEAD/lib/Resnet.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":"39037cdb0fe985b1"}},{"code_sha256_prefix":"9f120435a865e388","entry":"scale_torch","repo":"thygate/stable-diffusion-webui-depthmap-script","repo_kind":"listed","path":"src/depthmap_generation.py","file_url":"https://github.com/thygate/stable-diffusion-webui-depthmap-script/blob/HEAD/src/depthmap_generation.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":"9f120435a865e388"}},{"code_sha256_prefix":"5a951495ac113177","entry":"strip_prefix_if_present","repo":"thygate/stable-diffusion-webui-depthmap-script","repo_kind":"listed","path":"lib/net_tools.py","file_url":"https://github.com/thygate/stable-diffusion-webui-depthmap-script/blob/HEAD/lib/net_tools.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5a951495ac113177"}},{"code_sha256_prefix":"96c6be3581e1f391","entry":"weights_init","repo":"thygate/stable-diffusion-webui-depthmap-script","repo_kind":"listed","path":"inpaint/networks.py","file_url":"https://github.com/thygate/stable-diffusion-webui-depthmap-script/blob/HEAD/inpaint/networks.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"96c6be3581e1f391"}},{"code_sha256_prefix":"0314372534c03432","entry":"estimateleres","repo":"thygate/stable-diffusion-webui-depthmap-script","repo_kind":"listed","path":"src/depthmap_generation.py","file_url":"https://github.com/thygate/stable-diffusion-webui-depthmap-script/blob/HEAD/src/depthmap_generation.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":"0314372534c03432"}},{"code_sha256_prefix":"0d504dc72cd88b69","entry":"get_func","repo":"thygate/stable-diffusion-webui-depthmap-script","repo_kind":"listed","path":"lib/net_tools.py","file_url":"https://github.com/thygate/stable-diffusion-webui-depthmap-script/blob/HEAD/lib/net_tools.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":"0d504dc72cd88b69"}},{"code_sha256_prefix":"ff6eae1654f1ef39","entry":"resnext101_32x8d","repo":"thygate/stable-diffusion-webui-depthmap-script","repo_kind":"listed","path":"lib/Resnext_torch.py","file_url":"https://github.com/thygate/stable-diffusion-webui-depthmap-script/blob/HEAD/lib/Resnext_torch.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":"ff6eae1654f1ef39"}},{"code_sha256_prefix":"b189ed0149b76880","entry":"spectral_norm","repo":"thygate/stable-diffusion-webui-depthmap-script","repo_kind":"listed","path":"inpaint/networks.py","file_url":"https://github.com/thygate/stable-diffusion-webui-depthmap-script/blob/HEAD/inpaint/networks.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":"b189ed0149b76880"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}