Papers › ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation

ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation

27 Mar 2024CVPR 2024 1arXiv:2403.18807archive 2025-07-28

Suraj Patni, Aradhye Agarwal, Chetan Arora

In the absence of parallax cues, a learning-based single image depth estimation (SIDE) model relies heavily on shading and contextual cues in the image. While this simplicity is attractive, it is necessary to train such models on large and varied datasets, which are difficult to capture. It has been shown that using embeddings from pre-trained foundational models, such as CLIP, improves zero shot transfer in several applications. Taking inspiration from this, in our paper we explore the use of global image priors generated from a pre-trained ViT model to provide more detailed contextual information. We argue that the embedding vector from a ViT model, pre-trained on a large dataset, captures greater relevant information for SIDE than the usual route of generating pseudo image captions, followed by CLIP based text embeddings. Based on this idea, we propose a new SIDE model using a diffusion backbone which is conditioned on ViT embeddings. Our proposed design establishes a new state-of-the-art (SOTA) for SIDE on NYUv2 dataset, achieving Abs Rel error of 0.059 (14% improvement) compared to 0.069 by the current SOTA (VPD). And on KITTI dataset, achieving Sq Rel error of 0.139 (2% improvement) compared to 0.142 by the current SOTA (GEDepth). For zero-shot transfer with a model trained on NYUv2, we report mean relative improvement of (20%, 23%, 81%, 25%) over NeWCRFs on (Sun-RGBD, iBims1, DIODE, HyperSim) datasets, compared to (16%, 18%, 45%, 9%) by ZoeDepth. The project page is available at https://ecodepth-iitd.github.io

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

Syntology 15 code samples harvested from 1 repository linked to this paper: 11 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 3 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: official repository: 15 samples from 1 repository, 11 ran (6 with no instrument failure; 5 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

aradhye2002/ecodepth officialmentioned in papermentioned on GitHubpytorchSyntology: 15 samples, 11 ran (5 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.

Code Syntology ran Syntology

15 samples harvested: 11 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 5 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 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.

2ran · honoured contract
2ran · violated contract
3ran · our draft was wrong
2ran; the contract check could not run
2ran
4unverified

Licence: 15 of the 15 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 aradhye2002/ecodepth. “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.

aradhye2002/ecodepth official repository 15 samples, 11 ran (5 instrument-failed) · 4 unverified
Decoder in 210 papers model.py ran · metamorphic tier: deterministic licence not identified · pointer only · fbe2310addb47db4 · report fixture: returned Decoder · level recorded 2026-09-22
EmbeddingAdapter model.py ran licence not identified · pointer only · 21493ab89ab24490 · report fixture: signature texts:Tensor/2/float, gamma:Tensor/0/float · returned Tensor · level recorded 2026-09-24
compute_metrics in 208 papers model.py ran · our draft was wrong licence not identified · pointer only · e92e07aa1bf1be20 · report fixture: signature pred:Tensor/2/float, depth:Tensor/2/float, args:Args/0/? · returned dict · level recorded 2026-09-22
eigen_crop model.py ran · violated contract licence not identified · pointer only · f219540998580dc3 · report fixture: signature depth:Tensor/3/float · returned Tensor · level recorded 2026-09-22
garg_crop model.py ran · violated contract fingerprinted licence not identified · pointer only · 64e27454bc7d936a · report fixture: signature depth:Tensor/4/float · returned Tensor · level recorded 2026-09-22
get_optimizer in 228 papers model.py ran · our draft was wrong licence not identified · pointer only · 10c824c6cd3213ab · report fixture: signature model:callable/0/?, args:Args/0/?, no_decay_names:list/1/str · returned AdamW · level recorded 2026-09-22
no_crop model.py ran · honoured contract fingerprinted licence not identified · pointer only · 73c1d068e8ca81bd · report fixture: signature depth:Tensor/2/float · returned Tensor · level recorded 2026-09-22
pad in 85 papers model.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 36a4962041ede1c2 · report fixture: signature image:Tensor/4/float, desired_multiple_of:int/0/int · returned tuple · level recorded 2026-09-22
pad_to_make_square model.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted licence not identified · pointer only · 5d3ab34c6027afa8 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
silog model.py ran · honoured contract fingerprinted licence not identified · pointer only · 46cbbcee59b61483 · report fixture: signature pred:Tensor/2/float, target:Tensor/2/float · returned Tensor · level recorded 2026-09-22
unpad model.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence not identified · pointer only · 89728325857a7d3e · report fixture: signature image:Tensor/4/float, padding:tuple/1/int · returned Tensor · level recorded 2026-09-22
CIDE model.py unverified licence not identified · pointer only · fdf6b86f9b1766b1 · report
EcoDepth model.py unverified licence not identified · pointer only · 6159b9d4ff6618e7 · report
EcoDepthEncoder model.py unverified licence not identified · pointer only · b710c0ba3e6d33fd · report
custom_crop in 5 papers model.py unverified licence not identified · pointer only · 71964ceaab35f039 · 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 ECoDepth (graph method: ECoDepth). 17 bricks; individually on a fixture: 12 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. EcoDepth entry · level 0 · unverified · 6159b9d4ff6618e7
  2. Decoder model · level 1 · ran · fbe2310addb47db4
  3. EcoDepthEncoder model · level 0 · unverified · b710c0ba3e6d33fd
  4. compute_metrics helper · level 1 · ran · our draft was wrong · e92e07aa1bf1be20
  5. custom_crop helper · level 0 · unverified · 71964ceaab35f039
  6. eigen_crop helper · level 1 · ran · violated contract · f219540998580dc3
  7. garg_crop helper · level 1 · ran · violated contract · 64e27454bc7d936a
  8. get_optimizer helper · level 1 · ran · our draft was wrong · 10c824c6cd3213ab
  9. no_crop helper · level 1 · ran · honoured contract · 73c1d068e8ca81bd
  10. pad helper · level 1 · ran · our draft was wrong · 36a4962041ede1c2
  11. silog helper · level 1 · ran · honoured contract · 46cbbcee59b61483
  12. unpad helper · level 1 · ran; the contract check could not run (RAISES) · 89728325857a7d3e
  13. CIDE model · level 0 · unverified · fdf6b86f9b1766b1
  14. instantiate_from_config helper · level 0 · unverified · ef52d142b2c30ac2
  15. EmbeddingAdapter helper · level 1 · ran · 21493ab89ab24490
  16. pad_to_make_square helper · level 1 · ran; the contract check could not run (RAISES) · 5d3ab34c6027afa8
  17. get_obj_from_str helper · level 1 · ran · our draft was wrong · 221b2d116fdf1032

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="2403.18807") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Depth EstimationDepth PredictionMonocular Depth Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular Depth Estimation KITTI Eigen split ECoDepth Delta < 1.25 0.979 #12 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split ECoDepth Delta < 1.25^2 0.998 #12 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split ECoDepth Delta < 1.25^3 1.000 #12 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split ECoDepth RMSE 1.966 #12 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split ECoDepth RMSE log 0.074 #12 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split ECoDepth Sq Rel 0.139 #12 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split ECoDepth absolute relative error 0.048 #12 of 79 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 ECoDepth Delta < 1.25 0.978 #14 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 ECoDepth Delta < 1.25^2 0.997 #14 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 ECoDepth Delta < 1.25^3 0.999 #14 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 ECoDepth RMSE 0.218 #14 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 ECoDepth absolute relative error 0.059 #14 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 ECoDepth log 10 0.026 #14 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

AttentionDense ConnectionsDiffusionLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmaxVision Transformer

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