Papers › Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer

Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer

2 Jul 2019arXiv:1907.01341archive 2025-07-28

René Ranftl, Katrin Lasinger, David Hafner, Konrad Schindler, Vladlen Koltun

The success of monocular depth estimation relies on large and diverse training sets. Due to the challenges associated with acquiring dense ground-truth depth across different environments at scale, a number of datasets with distinct characteristics and biases have emerged. We develop tools that enable mixing multiple datasets during training, even if their annotations are incompatible. In particular, we propose a robust training objective that is invariant to changes in depth range and scale, advocate the use of principled multi-objective learning to combine data from different sources, and highlight the importance of pretraining encoders on auxiliary tasks. Armed with these tools, we experiment with five diverse training datasets, including a new, massive data source: 3D films. To demonstrate the generalization power of our approach we use zero-shot cross-dataset transfer}, i.e. we evaluate on datasets that were not seen during training. The experiments confirm that mixing data from complementary sources greatly improves monocular depth estimation. Our approach clearly outperforms competing methods across diverse datasets, setting a new state of the art for monocular depth estimation. Some results are shown in the supplementary video at https://youtu.be/D46FzVyL9I8

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

No sample from the archive's official repository (intel-isl/MiDaS) is linked to this paper; the 17 samples below come from 4 community repositories. Syntology harvested code from intel-isl/MiDaS for another paper.

intel-isl/MiDaS: 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.

Syntology 17 code samples harvested from 4 repositories linked to this paper: 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. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 17 samples from 4 repositories, 13 ran (11 with no instrument failure; 2 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.

No sample is linked to this paper from 5 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.

16 repositories listed; official and paper-mentioned ones first.

intel-isl/MiDaS officialmentioned in papermentioned 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
AbirKhan96/Intel-ISL-MiDaS mentioned on GitHubpytorchSyntology: not harvested report
JeffreyMagee/Distance-measure-based-on-depth-estimation mentioned on GitHubpytorchSyntology: not harvested report
Mind23-2/MindCode-57 mentioned on GitHubmindsporeSyntology: not harvested report
ahmedmostafa0x61/Depth_Estimation 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
alexeyab/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
anlok/depthmap-loktev mentioned on GitHubpytorchMITSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
freshtan/midas_v2 mentioned on GitHubmindsporeApache-2.0Syntology: 8 samples, 6 ran (1 instrument-failed) · 2 unverified report
isl-org/MiDaS mentioned on GitHubpytorchSyntology: 3 samples, 1 ran (1 instrument-failed) · 2 unverified report
lasinger/3DVideos2Stereo mentioned on GitHubMITSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
picsart-ai-research/text2video-zero mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
prakashSidd18/blind_augmentation mentioned on GitHubpytorchSyntology: not harvested report
scut-math-srp/Distance-measure-based-on-depth-estimation mentioned on GitHubpytorchSyntology: not harvested report
shubham0204/Realtime_MiDaS_Depth_Estimation_Android mentioned on GitHubtfSyntology: not harvested report
vishal-kataria/MiDaS-master 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
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. 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

17 samples harvested: 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. “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
2ran · our draft was wrong
10ran
4unverified

Licence: 1 of the 17 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 4 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. “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.

anlok/depthmap-loktev community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
apply_min_size in 5 papers models/transforms.py ran MIT (permissive) · 8d4e5ab503856d09 · report fixture: signature sample:dict/0/?, size:tuple/1/int, image_interpolation_method:int/0/int · returned tuple · level recorded 2026-09-24
read_image in 73 papers utils.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · fa28021adde0f186 · report fixture: signature path:str/0/str · returned ndarray · level recorded 2026-09-24
read_pfm in 24 papers utils.py ran MIT (permissive) · 188a19865f88f383 · report fixture: signature path:str/0/str · returned tuple · level recorded 2026-09-24
resize_image in 74 papers utils.py ran fingerprinted MIT (permissive) · 80ea105639cd9efd · report fixture: signature img:ndarray/3/int · returned Tensor · level recorded 2026-09-24
freshtan/midas_v2 community (archive-listed) 8 samples, 6 ran (1 instrument-failed) · 2 unverified
associate in 5 papers preprocess/associate.py ran Apache-2.0 (permissive) · c0f7dd2e78f91f10 · report fixture: signature first_list1:dict/0/?, second_list1:dict/0/?, offset:float/0/float, max_difference:float/0/float · returned list · level recorded 2026-09-24
merge in 85 papers src/config.py ran · our draft was wrong Apache-2.0 (permissive) · b9e24c3e3e0e88a7 · report fixture: signature args:Namespace/0/?, cfg:dict/0/? · returned dict · level recorded 2026-09-22
parse_cli_to_yaml in 29 papers src/config.py ran Apache-2.0 (permissive) · 738456e1b7388e7e · report fixture: signature parser:ArgumentParser/0/?, cfg:dict/0/?, helper:dict/0/?, choices:dict/0/?, cfg_path:str/0/str · returned Namespace · level recorded 2026-09-24
parse_yaml in 32 papers src/config.py ran Apache-2.0 (permissive) · 96a9939953d5992d · report fixture: signature yaml_path:str/0/str · returned tuple · level recorded 2026-09-25
read_file_list in 9 papers preprocess/associate.py ran Apache-2.0 (permissive) · 780a0dcc75fb0c82 · report fixture: signature filename:str/0/str · returned dict · level recorded 2026-09-24
write_depth src/util.py ran Apache-2.0 (permissive) · d0f2d7d797bf8806 · report fixture: signature path:str/0/str, depth:ndarray/2/float, bits:int/0/int · returned ndarray · level recorded 2026-09-24
depth_read_kitti src/util.py unverified Apache-2.0 (permissive) · 98b6d75cef37e16d · report
get_eval_result postprocess.py unverified Apache-2.0 (permissive) · c3d82023511f51f2 · report
isl-org/MiDaS community (archive-listed) 3 samples, 1 ran (1 instrument-failed) · 2 unverified
patch_embed_forward midas/backbones/beit.py ran · our draft was wrong MIT (permissive) · a3b0b33caf369c41 · report fixture: signature self:callable/0/?, x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
attention_forward in 8 papers midas/backbones/beit.py unverified MIT (permissive) · cc0b35f6d7118df1 · report
forward_beit midas/backbones/beit.py unverified MIT (permissive) · 62d386dcfc041ca8 · report
lasinger/3DVideos2Stereo community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
processShotFile genTraining_recurr.py ran MIT (permissive) · 079a28e19eb8f028 · report fixture: signature video:str/0/str, shotFile:str/0/str · returned list · level recorded 2026-09-24
read_flow get_disp_and_uncertainty.py ran fingerprinted MIT (permissive) · 484108557b544812 · report fixture: signature filename:str/0/str · returned tuple · level recorded 2026-09-24

Tasks

Depth EstimationMonocular Depth Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Depth Estimation DCM MIDAS Abs Rel 0.309 #2 of 3 Archive leaderboard report
Depth Estimation DCM MIDAS RMSE 1.033 #2 of 3 Archive leaderboard report
Depth Estimation DCM MIDAS RMSE log 0.375 #2 of 3 Archive leaderboard report
Depth Estimation DCM MIDAS Sq Rel 0.381 #2 of 3 Archive leaderboard report
Depth Estimation eBDtheque MIDAS Abs Rel 0.419 #2 of 3 Archive leaderboard report
Depth Estimation eBDtheque MIDAS RMSE 1.416 #2 of 3 Archive leaderboard report
Depth Estimation eBDtheque MIDAS RMSE log 0.659 #2 of 3 Archive leaderboard report
Depth Estimation eBDtheque MIDAS Sq Rel 0.503 #2 of 3 Archive leaderboard report
Monocular Depth Estimation ETH3D MiDaS Delta < 1.25 0.0752 #10 of 10 Archive leaderboard report
Monocular Depth Estimation ETH3D MiDaS absolute relative error 0.0184 #10 of 10 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.

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