Papers › VA-DepthNet: A Variational Approach to Single Image Depth Prediction

VA-DepthNet: A Variational Approach to Single Image Depth Prediction

13 Feb 2023arXiv:2302.06556archive 2025-07-28

Ce Liu, Suryansh Kumar, Shuhang Gu, Radu Timofte, Luc van Gool

We introduce VA-DepthNet, a simple, effective, and accurate deep neural network approach for the single-image depth prediction (SIDP) problem. The proposed approach advocates using classical first-order variational constraints for this problem. While state-of-the-art deep neural network methods for SIDP learn the scene depth from images in a supervised setting, they often overlook the invaluable invariances and priors in the rigid scene space, such as the regularity of the scene. The paper's main contribution is to reveal the benefit of classical and well-founded variational constraints in the neural network design for the SIDP task. It is shown that imposing first-order variational constraints in the scene space together with popular encoder-decoder-based network architecture design provides excellent results for the supervised SIDP task. The imposed first-order variational constraint makes the network aware of the depth gradient in the scene space, i.e., regularity. The paper demonstrates the usefulness of the proposed approach via extensive evaluation and ablation analysis over several benchmark datasets, such as KITTI, NYU Depth V2, and SUN RGB-D. The VA-DepthNet at test time shows considerable improvements in depth prediction accuracy compared to the prior art and is accurate also at high-frequency regions in the scene space. At the time of writing this paper, our method -- labeled as VA-DepthNet, when tested on the KITTI depth-prediction evaluation set benchmarks, shows state-of-the-art results, and is the top-performing published approach.

PaperPDFCodeCode 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 5 code samples harvested from 1 repository linked to this paper: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 5 samples from 1 repository, 3 ran (2 with no instrument failure; 1 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.

cnexah/va-depthnet officialmentioned in paperpytorchSyntology: 5 samples, 3 ran (1 instrument-failed) · 2 unverified report
MindSpore-MS-Code2/code0 mindsporeSyntology: not harvested 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

5 samples harvested: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 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.

1ran; the contract check could not run
2ran
2unverified

Licence: 0 of the 5 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 cnexah/va-depthnet. “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. 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.

cnexah/va-depthnet official repository 5 samples, 3 ran (1 instrument-failed) · 2 unverified
SILogLoss vadepthnet/networks/vadepthnet.py ran · metamorphic tier: invariant MIT (permissive) · c4f5c76bb4e41b61 · report fixture: signature feat:dict/0/?, gts:Tensor/4/float · returned Tensor · level recorded 2026-09-22
VarLoss vadepthnet/networks/vadepthnet.py ran fingerprinted MIT (permissive) · b3ce217068db35f0 · report fixture: signature x:Tensor/4/float, d:Tensor/4/float, gts:Tensor/4/float · returned Tensor · level recorded 2026-09-24
pixel_unshuffle in 15 papers
census: 4 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
vadepthnet/networks/vadepthnet.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · b48ac716ae100201 · report fixture: signature fm:Tensor/4/float, r:int/0/int · returned Tensor · level recorded 2026-09-22
VADepthNet vadepthnet/networks/vadepthnet.py unverified MIT (permissive) · ab355cc06280fbc3 · report
VarLayer vadepthnet/networks/vadepthnet.py unverified MIT (permissive) · 134adf29303058bb · 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 VA-DepthNet (graph method: VA-DepthNet). 26 bricks; individually on a fixture: 16 ran (of which 7 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified. The assembly has not been run end-to-end.

  1. VADepthNet entry · level 0 · unverified · ab355cc06280fbc3
  2. MetricLayer metric · level 1 · ran · e42969b7bf86747e
  3. OutConv model · level 1 · ran · 96be5d7e36e0d6f8
  4. Refine model · level 1 · ran · 22c1941ae236e18b
  5. SILogLoss loss · level 1 · ran · c4f5c76bb4e41b61
  6. SwinTransformer helper · level 0 · unverified · 0ba2498ffe0b4454
  7. Up model · level 1 · ran · ca0383a1bf504494
  8. VarLayer model · level 0 · unverified · 134adf29303058bb
  9. VarLoss loss · level 1 · ran · b3ce217068db35f0
  10. pixel_unshuffle helper · level 1 · ran; the contract check could not run (RAISES) · b48ac716ae100201
  11. BasicLayer helper · level 0 · unverified · 4474d70757f8bbdf
  12. PatchEmbed helper · level 1 · ran · 119f41dde4cc5c1b
  13. PatchMerging helper · level 1 · ran · be586c7612ce6beb
  14. load_checkpoint helper · level 0 · unverified · 99a1fadf82ab1b67
  15. DoubleConv model · level 0 · unverified · 533554e0f3ae3b96
  16. SwinTransformerBlock helper · level 0 · unverified · a1aa4e604c6c304d
  17. window_partition helper · level 2 · ran; the contract check could not run · 144d10b49baeb8a6
  18. _load_checkpoint helper · level 1 · ran · our draft was wrong · 51d3a176d1206333
  19. load_state_dict helper · level 0 · unverified · b9bb350524a8fa9f
  20. Mlp helper · level 1 · ran · ab49e7dfb4c6af7e
  21. WindowAttention helper · level 1 · ran · e72484de5dddeb6b
  22. window_reverse helper · level 1 · ran · our draft was wrong · 61bf152e6a42a184
  23. get_torchvision_models helper · level 1 · ran · a1b8bb2acb22a0ec
  24. load_url_dist helper · level 0 · unverified · 3b1a511338023426
  25. get_dist_info helper · level 1 · ran · a91567db5e6c35b4
  26. is_module_wrapper helper · level 0 · unverified · 9b9dd29ad0d626a0

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="2302.06556") 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 NYU-Depth V2 VA-DepthNet(SwinV1-L) Delta < 1.25 0.937 #31 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 VA-DepthNet(SwinV1-L) Delta < 1.25^2 0.992 #31 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 VA-DepthNet(SwinV1-L) Delta < 1.25^3 0.999 #31 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 VA-DepthNet(SwinV1-L) RMSE 0.304 #31 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 VA-DepthNet(SwinV1-L) absolute relative error 0.086 #31 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 VA-DepthNet(SwinV1-L) log 10 0.037 #31 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

AWARETest

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