Papers › UniDepth: Universal Monocular Metric Depth Estimation

UniDepth: Universal Monocular Metric Depth Estimation

27 Mar 2024CVPR 2024 1arXiv:2403.18913archive 2025-07-28

Luigi Piccinelli, Yung-Hsu Yang, Christos Sakaridis, Mattia Segu, Siyuan Li, Luc van Gool, Fisher Yu

Accurate monocular metric depth estimation (MMDE) is crucial to solving downstream tasks in 3D perception and modeling. However, the remarkable accuracy of recent MMDE methods is confined to their training domains. These methods fail to generalize to unseen domains even in the presence of moderate domain gaps, which hinders their practical applicability. We propose a new model, UniDepth, capable of reconstructing metric 3D scenes from solely single images across domains. Departing from the existing MMDE methods, UniDepth directly predicts metric 3D points from the input image at inference time without any additional information, striving for a universal and flexible MMDE solution. In particular, UniDepth implements a self-promptable camera module predicting dense camera representation to condition depth features. Our model exploits a pseudo-spherical output representation, which disentangles camera and depth representations. In addition, we propose a geometric invariance loss that promotes the invariance of camera-prompted depth features. Thorough evaluations on ten datasets in a zero-shot regime consistently demonstrate the superior performance of UniDepth, even when compared with methods directly trained on the testing domains. Code and models are available at: https://github.com/lpiccinelli-eth/unidepth

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2403.18913")

Code

Syntology Ran 15 of 26 code samples harvested from 3 repositories linked to this paper; 11 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 6 ran · fixture could not drive it; 6 ran with no contract checked.

By repository: official repository: 23 samples from 1 repository, 15 ran; community (archive-listed): 3 samples from 2 repositories, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

lpiccinelli-eth/unidepth officialmentioned in papermentioned on GitHubpytorch report
henry123-boy/SpaTracker mentioned on GitHubpytorch 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

26 samples harvested; 15 ran; 0 honoured the contract we drafted; 11 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · our draft was wrong
6ran · fixture could not drive it
6ran
11unverified

Licence: 25 of the 26 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 3 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

ListAdapter lpiccinelli-eth/unidepth/unidepth/models/unidepthv1/unidepthv1.py official repository ran · metamorphic tier: invariant licence not identified · pointer only · 5e4cca49cac4d80e · report
_paddings lpiccinelli-eth/unidepth/unidepth/models/unidepthv1/unidepthv1.py official repository ran · fixture could not drive it fingerprinted licence not identified · pointer only · 95084bc240332452 · report
_postprocess lpiccinelli-eth/unidepth/unidepth/models/unidepthv1/unidepthv1.py official repository ran licence not identified · pointer only · d5d4d422a21b0a05 · report
_preprocess lpiccinelli-eth/unidepth/unidepth/models/unidepthv1/unidepthv1.py official repository ran · our draft was wrong licence not identified · pointer only · 27638cf0225e17aa · report
_shapes lpiccinelli-eth/unidepth/unidepth/models/unidepthv1/unidepthv1.py official repository ran · fixture could not drive it fingerprinted licence not identified · pointer only · 6d5d386b010a90cc · report
flat_interpolate lpiccinelli-eth/unidepth/unidepth/models/unidepthv1/unidepthv1.py official repository ran · fixture could not drive it licence not identified · pointer only · ab5f0cf7db8829b0 · report
get_params lpiccinelli-eth/unidepth/unidepth/models/unidepthv1/unidepthv1.py official repository ran licence not identified · pointer only · 1a61b6729f16be14 · report
get_rank lpiccinelli-eth/unidepth/unidepth/models/unidepthv1/unidepthv1.py official repository ran licence not identified · pointer only · 21f13ea283351acc · report
is_dist_avail_and_initialized lpiccinelli-eth/unidepth/unidepth/models/unidepthv1/unidepthv1.py official repository ran licence not identified · pointer only · 776d3f86791004d1 · report
is_main_process lpiccinelli-eth/unidepth/unidepth/models/unidepthv1/unidepthv1.py official repository ran licence not identified · pointer only · e17a1e0c67eaf7b8 · report
match_gt lpiccinelli-eth/unidepth/unidepth/models/unidepthv1/unidepthv1.py official repository ran · fixture could not drive it licence not identified · pointer only · c54375eea881eda0 · report
match_intrinsics lpiccinelli-eth/unidepth/unidepth/models/unidepthv1/unidepthv1.py official repository ran · our draft was wrong licence not identified · pointer only · be3fb71a3dda1ed6 · report
max_stack lpiccinelli-eth/unidepth/unidepth/models/unidepthv1/unidepthv1.py official repository ran · fixture could not drive it licence not identified · pointer only · 0d444610e9aa423f · report
rsh_cart_8 lpiccinelli-eth/unidepth/unidepth/models/unidepthv1/unidepthv1.py official repository ran · our draft was wrong fingerprinted licence not identified · pointer only · c7571a839bb7916c · report
spherical_zbuffer_to_euclidean lpiccinelli-eth/unidepth/unidepth/models/unidepthv1/unidepthv1.py official repository ran · fixture could not drive it licence not identified · pointer only · 2f4bab52957d3b0e · report
AttentionBlock lpiccinelli-eth/unidepth/unidepth/models/unidepthv1/unidepthv1.py official repository unverified licence not identified · pointer only · 3bbe2dc4e9f7b54b · report
CameraHead lpiccinelli-eth/unidepth/unidepth/models/unidepthv1/unidepthv1.py official repository unverified licence not identified · pointer only · bfbc779ee61e385c · report
Decoder lpiccinelli-eth/unidepth/unidepth/models/unidepthv1/unidepthv1.py official repository unverified licence not identified · pointer only · 4fed83b01592cd1b · report
DepthHead lpiccinelli-eth/unidepth/unidepth/models/unidepthv1/unidepthv1.py official repository unverified licence not identified · pointer only · 50c790a0244300f6 · report
ProfileMethod lpiccinelli-eth/unidepth/unidepth/models/unidepthv1/unidepthv1.py official repository unverified licence not identified · pointer only · 2a686a5ac19872b4 · report
UniDepthV1 lpiccinelli-eth/unidepth/unidepth/models/unidepthv1/unidepthv1.py official repository unverified licence not identified · pointer only · 5e7bb5ae1c94af71 · report
generate_rays lpiccinelli-eth/unidepth/unidepth/models/unidepthv1/unidepthv1.py official repository unverified licence not identified · pointer only · c136d0e4ba11d802 · report
profile_method lpiccinelli-eth/unidepth/unidepth/models/unidepthv1/unidepthv1.py official repository unverified licence not identified · pointer only · 4fa984f2f2be8ec1 · report
DPTHead henry123-boy/SpaTracker/models/monoD/depth_anything/dpt.py community (archive-listed) unverified licence not identified · pointer only · 5f8c327ff4b304d4 · report
DPT_DINOv2 henry123-boy/SpaTracker/models/monoD/depth_anything/dpt.py community (archive-listed) unverified licence not identified · pointer only · c918b2b60a6b0cf2 · report
colorize_map ibaiGorordo/ONNX-Unidepth-Monocular-Metric-Depth-Estimation/unidepth/UniDepth.py community (archive-listed) unverified MIT (permissive) · b270379104db863c · report

Tasks

Depth EstimationMonocular Depth Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular Depth Estimation KITTI Eigen split UniDepth (Zero-shot) Delta < 1.25 0.986 #7 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split UniDepth (Zero-shot) Delta < 1.25^2 0.998 #7 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split UniDepth (Zero-shot) Delta < 1.25^3 0.999 #7 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split UniDepth (Zero-shot) RMSE 1.75 #7 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split UniDepth (Zero-shot) RMSE log 0.064 #7 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split UniDepth (Zero-shot) absolute relative error 0.042 #7 of 79 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 UniDepth (Zero-shot) Delta < 1.25 0.984 #12 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 UniDepth (Zero-shot) Delta < 1.25^2 0.997 #12 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 UniDepth (Zero-shot) Delta < 1.25^3 0.999 #12 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 UniDepth (Zero-shot) RMSE 0.201 #12 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 UniDepth (Zero-shot) absolute relative error 0.058 #12 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 UniDepth (Zero-shot) log 10 0.024 #12 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.

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