Papers › ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth

ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth

23 Feb 2023arXiv:2302.12288archive 2025-07-28

Shariq Farooq Bhat, Reiner Birkl, Diana Wofk, Peter Wonka, Matthias Müller

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 .

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples: 15 from 2 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 16: 12 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 9 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 14 samples from 1 repository, 10 ran (3 with no instrument failure; 7 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 12 samples that ran have no recorded date.

isl-org/ZoeDepth officialmentioned in papermentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
GuidoManni/BodySLAM mentioned on GitHubpytorchSyntology: not harvested report
cake-lab/Mobile-AR-Depth-Estimation mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Towards Zero-Shot Scale-Aware Monocular Depth Estimation (arXiv:2306.17253; that paper's own run record: 18 ran (of which 10 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
intel-isl/MiDaS mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Vision Transformers for Dense Prediction (arXiv:2103.13413; that paper's own run record: 65 ran (of which 19 constructed an object rather than computing a result; 32 with no instrument failure: 0 honoured, 0 violated, 32 with no contract checked; 33 where Syntology's instrument failed) · 51 unverified); nothing checks that they implement this paper's method. report
isl-org/MiDaS mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer (arXiv:1907.01341; that paper's own run record: 13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
thygate/stable-diffusion-webui-depthmap-script mentioned on GitHubpytorchMITSyntology: 14 samples, 10 ran (7 instrument-failed) · 4 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

16 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 9 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
8ran · our draft was wrong
1ran; the contract check could not run
2ran
4unverified

Licence: 10 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. For 9 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample is listed last, in a group without a repository. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

isl-org/ZoeDepth official repository 1 sample, 1 ran (1 instrument-failed) · 0 unverified
infer in 29 papers evaluate.py ran · our draft was wrong MIT (permissive) · 8ffddb7d6410c4f1 · report fixture: signature model:callable/0/?, images:Tensor/4/float · returned Tensor · level recorded 2026-09-22
thygate/stable-diffusion-webui-depthmap-script community (archive-listed) 14 samples, 10 ran (7 instrument-failed) · 4 unverified
conv1x1 in 691 papers lib/Resnext_torch.py ran · our draft was wrong MIT (permissive) · d9def42110729a85 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
conv3x3 in 1,376 papers lib/Resnext_torch.py ran · our draft was wrong MIT (permissive) · 160bb14bd76201b4 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned Conv2d · level recorded, date not recorded
conv3x3 in 1,376 papers lib/Resnet.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · fac5364e2f53c6db · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
estimatezoedepth src/depthmap_generation.py ran MIT (permissive) · 13416aca1c543254 · report fixture: signature img:Image/0/?, model:callable/0/?, w:int/0/int, h:int/0/int · returned ndarray · level recorded 2026-09-25
get_installed_version install.py ran fingerprinted MIT (permissive) · a467686f61537560 · report fixture: signature package:str/0/str · returned str · level recorded 2026-09-25
resnet18 in 432 papers lib/Resnet.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 42823db097a59e8e · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-24
resnet34 in 148 papers lib/Resnet.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 39037cdb0fe985b1 · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-24
scale_torch src/depthmap_generation.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 9f120435a865e388 · report fixture: signature img:ndarray/3/int · returned Tensor · level recorded 2026-09-24
strip_prefix_if_present in 16 papers lib/net_tools.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 5a951495ac113177 · report fixture: signature state_dict:dict/0/?, prefix:str/0/str · returned OrderedDict · level recorded 2026-09-22
weights_init in 44 papers inpaint/networks.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 96c6be3581e1f391 · report fixture: signature init_type:str/0/str · returned function · level recorded 2026-09-22
estimateleres src/depthmap_generation.py unverified MIT (permissive) · 0314372534c03432 · report
get_func in 5 papers lib/net_tools.py unverified MIT (permissive) here; the stored copy is pointer only · 0d504dc72cd88b69 · report
resnext101_32x8d lib/Resnext_torch.py unverified MIT (permissive) here; the stored copy is pointer only · ff6eae1654f1ef39 · report
spectral_norm in 42 papers inpaint/networks.py unverified MIT (permissive) here; the stored copy is pointer only · b189ed0149b76880 · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
load_ckpt in 31 papers repository not located ran; the contract check could not run (DEP_MISSING) · metamorphic tier: deterministic licence of this copy not recorded · 6ff08048a8305588 · report fixture: signature config:MinimalConfig/0/?, model:callable/0/?, checkpoint_dir:str/0/str, ckpt_type:str/0/str · returned MinimalModel · level recorded 2026-09-22

Tasks

Depth EstimationMonocular Depth EstimationZero-shot Generalization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular Depth Estimation NYU-Depth V2 ZoeD-M12-N Delta < 1.25 0.955 #26 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 ZoeD-M12-N Delta < 1.25^2 0.995 #26 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 ZoeD-M12-N Delta < 1.25^3 0.999 #26 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 ZoeD-M12-N RMSE 0.270 #26 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 ZoeD-M12-N absolute relative error 0.075 #26 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 ZoeD-M12-N log 10 0.032 #26 of 85 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAdaptiveBinsAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections