Papers › Towards Zero-Shot Scale-Aware Monocular Depth Estimation

Towards Zero-Shot Scale-Aware Monocular Depth Estimation

29 Jun 2023ICCV 2023 1arXiv:2306.17253archive 2025-07-28

Vitor Guizilini, Igor Vasiljevic, Dian Chen, Rares Ambrus, Adrien Gaidon

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.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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

The archive's official repository (TRI-ML/vidar) was not harvested; the 21 samples below come from 1 community repository.

Syntology 21 code samples harvested from 1 repository linked to this paper: 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. Where Syntology's instrument failed: 6 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 21 samples from 1 repository, 18 ran (10 with no instrument failure; 8 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

TRI-ML/vidar officialmentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
cake-lab/Mobile-AR-Depth-Estimation mentioned on GitHubpytorchSyntology: 21 samples, 18 ran (8 instrument-failed) · 3 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.

Code Syntology ran Syntology

21 samples harvested: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

6ran · our draft was wrong
2ran; the contract check could not run
10ran
3unverified

Licence: 21 of the 21 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from cake-lab/Mobile-AR-Depth-Estimation. “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”. For 6 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

cake-lab/Mobile-AR-Depth-Estimation community (archive-listed) 21 samples, 18 ran (8 instrument-failed) · 3 unverified
AttractorLayer models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py ran GPL-3.0 (copyleft) · pointer only · dcc68d2d5168c6d2 · report fixture: returned AttractorLayer · level recorded 2026-09-22
AttractorLayerUnnormed models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py ran GPL-3.0 (copyleft) · pointer only · 279b5ed1a765f954 · report fixture: returned AttractorLayerUnnormed · level recorded 2026-09-22
ConditionalLogBinomial models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py ran GPL-3.0 (copyleft) · pointer only · af08204fe220399a · report fixture: returned ConditionalLogBinomial · level recorded 2026-09-22
DepthModel models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py ran GPL-3.0 (copyleft) · pointer only · 09c47daa6157e163 · report fixture: returned DepthModel · level recorded 2026-09-22
LogBinomial models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py ran fingerprinted GPL-3.0 (copyleft) · pointer only · a6d50c03a384b9f9 · report fixture: returned LogBinomial · level recorded 2026-09-22
PrepForMidas models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py ran fingerprinted GPL-3.0 (copyleft) · pointer only · 40291ed283381627 · report fixture: returned PrepForMidas · level recorded 2026-09-22
Projector in 18 papers models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py ran GPL-3.0 (copyleft) · pointer only · c7d5b9ffb26b16f9 · report fixture: returned Projector · level recorded 2026-09-22
Resize models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py ran fingerprinted GPL-3.0 (copyleft) · pointer only · 02cce835de2b105e · report fixture: returned Resize · level recorded 2026-09-22
SeedBinRegressor models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py ran GPL-3.0 (copyleft) · pointer only · 36f362b347043d76 · report fixture: returned SeedBinRegressor · level recorded 2026-09-22
SeedBinRegressorUnnormed models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py ran GPL-3.0 (copyleft) · pointer only · acc1438609c7087b · report fixture: returned SeedBinRegressorUnnormed · level recorded 2026-09-22
denormalize in 64 papers
census: 9 implementations from 11 papers, 8 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 1 of 4, arg 1: rank 4, kind float, dtype float32
models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py ran · our draft was wrong fingerprinted GPL-3.0 (copyleft) · pointer only · 0a23d935ca395f43 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
exp_attractor models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py ran; the contract check could not run (RAISES) GPL-3.0 (copyleft) · pointer only · 718d04d747cf4760 · report fixture: returned Tensor · level recorded 2026-09-22
get_activation in 218 papers models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 5e36e11ad4768925 · report fixture: signature name:str/0/str, bank:dict/0/? · returned function · level recorded 2026-09-22
inv_attractor models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py ran; the contract check could not run (RAISES) GPL-3.0 (copyleft) · pointer only · 4b7edbe448ed6655 · report fixture: returned Tensor · level recorded 2026-09-22
load_state_dict in 114 papers models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 98303a9870582d70 · report fixture: signature model:callable/0/?, state_dict:dict/0/? · returned SimpleModel · level recorded 2026-09-22
load_state_dict_from_url in 8 papers models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · fc85e8c7a4e15c37 · report fixture: signature model:callable/0/?, url:str/0/str, progress:bool/0/bool · returned SimpleModel · level recorded 2026-09-22
load_wts models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 0da54450ea6be402 · report fixture: signature model:callable/0/?, checkpoint_path:str/0/str · returned SimpleModel · level recorded 2026-09-22
log_binom models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py ran · our draft was wrong fingerprinted GPL-3.0 (copyleft) · pointer only · ace543f1e5d9a720 · report fixture: signature n:Tensor/2/float, k:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22
MidasCore models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py unverified GPL-3.0 (copyleft) · pointer only · 1dac62be1b99a756 · report
ZoeDepth models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py unverified GPL-3.0 (copyleft) · pointer only · 26b182be61087f4f · report
load_state_from_resource models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py unverified GPL-3.0 (copyleft) · pointer only · a7dc96eec669ee52 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Zero-Shot Scale-Aware Monocular Depth Estimation (graph method: Zero-Shot Scale-Aware Monocular Depth Estimation). 21 bricks; individually on a fixture: 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. The assembly has not been run end-to-end.

  1. ZoeDepth entry · level 0 · unverified · 26b182be61087f4f
  2. AttractorLayer helper · level 1 · ran · dcc68d2d5168c6d2
  3. AttractorLayerUnnormed helper · level 1 · ran · 279b5ed1a765f954
  4. ConditionalLogBinomial helper · level 1 · ran · af08204fe220399a
  5. DepthModel helper · level 1 · ran · 09c47daa6157e163
  6. MidasCore helper · level 0 · unverified · 1dac62be1b99a756
  7. Projector helper · level 1 · ran · c7d5b9ffb26b16f9
  8. SeedBinRegressor helper · level 1 · ran · 36f362b347043d76
  9. SeedBinRegressorUnnormed helper · level 1 · ran · acc1438609c7087b
  10. load_state_from_resource helper · level 0 · unverified · a7dc96eec669ee52
  11. exp_attractor helper · level 1 · ran; the contract check could not run (RAISES) · 718d04d747cf4760
  12. inv_attractor helper · level 1 · ran; the contract check could not run (RAISES) · 4b7edbe448ed6655
  13. LogBinomial helper · level 1 · ran · a6d50c03a384b9f9
  14. PrepForMidas helper · level 1 · ran · 40291ed283381627
  15. denormalize helper · level 1 · ran · our draft was wrong · 0a23d935ca395f43
  16. get_activation helper · level 1 · ran · our draft was wrong · 5e36e11ad4768925
  17. load_state_dict_from_url helper · level 1 · ran · our draft was wrong · fc85e8c7a4e15c37
  18. load_wts helper · level 1 · ran · our draft was wrong · 0da54450ea6be402
  19. log_binom helper · level 1 · ran · our draft was wrong · ace543f1e5d9a720
  20. Resize helper · level 1 · ran · 02cce835de2b105e
  21. load_state_dict helper · level 1 · ran · our draft was wrong · 98303a9870582d70

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2306.17253") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DecoderDepth EstimationMonocular Depth Estimation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Focus

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