Papers › WorDepth: Variational Language Prior for Monocular Depth Estimation

WorDepth: Variational Language Prior for Monocular Depth Estimation

4 Apr 2024CVPR 2024 1arXiv:2404.03635archive 2025-07-28

Ziyao Zeng, Daniel Wang, Fengyu Yang, Hyoungseob Park, Yangchao Wu, Stefano Soatto, Byung-Woo Hong, Dong Lao, Alex Wong

Three-dimensional (3D) reconstruction from a single image is an ill-posed problem with inherent ambiguities, i.e. scale. Predicting a 3D scene from text description(s) is similarly ill-posed, i.e. spatial arrangements of objects described. We investigate the question of whether two inherently ambiguous modalities can be used in conjunction to produce metric-scaled reconstructions. To test this, we focus on monocular depth estimation, the problem of predicting a dense depth map from a single image, but with an additional text caption describing the scene. To this end, we begin by encoding the text caption as a mean and standard deviation; using a variational framework, we learn the distribution of the plausible metric reconstructions of 3D scenes corresponding to the text captions as a prior. To "select" a specific reconstruction or depth map, we encode the given image through a conditional sampler that samples from the latent space of the variational text encoder, which is then decoded to the output depth map. Our approach is trained alternatingly between the text and image branches: in one optimization step, we predict the mean and standard deviation from the text description and sample from a standard Gaussian, and in the other, we sample using a (image) conditional sampler. Once trained, we directly predict depth from the encoded text using the conditional sampler. We demonstrate our approach on indoor (NYUv2) and outdoor (KITTI) scenarios, where we show that language can consistently improve performance in both.

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 26 code samples harvested from 1 repository linked to this paper: 16 ran (of which 6 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 26 samples from 1 repository, 16 ran (12 with no instrument failure; 4 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. 2 of the 16 samples that ran have no recorded date.

adonis-galaxy/wordepth officialmentioned in papermentioned on GitHubpytorchSyntology: 26 samples, 16 ran (4 instrument-failed) · 10 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

26 samples harvested: 16 ran (of which 6 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 10 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.

2ran · honoured contract
3ran · our draft was wrong
1ran; the contract check could not run
10ran
10unverified

Licence: 26 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 adonis-galaxy/wordepth. “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 4 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.

adonis-galaxy/wordepth official repository 26 samples, 16 ran (4 instrument-failed) · 10 unverified
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
src/networks/swin_transformer.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 144d10b49baeb8a6 · report fixture: signature x:Tensor/4/float, window_size:int/0/int · returned Tensor · level recorded, date not recorded
EpsLayer src/networks/wordepth.py ran · metamorphic tier: deterministic no licence file found · pointer only · 78636f3e5d41d22f · report fixture: returned EpsLayer · level recorded 2026-09-22
MetricLayer src/networks/wordepth.py ran · metamorphic tier: deterministic no licence file found · pointer only · e42969b7bf86747e · report fixture: returned MetricLayer · level recorded 2026-09-22
OutConv in 9 papers src/networks/wordepth.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 96be5d7e36e0d6f8 · report fixture: returned OutConv · level recorded 2026-09-22
Refine in 10 papers src/networks/wordepth.py ran no licence file found · pointer only · 22c1941ae236e18b · report fixture: signature feat:Tensor/4/float, depth:Tensor/4/float · returned tuple · level recorded 2026-09-24
SILogLoss src/networks/wordepth.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · f78085ec460691c1 · report fixture: returned SILogLoss · level recorded 2026-09-22
Text_Encoder src/networks/wordepth.py ran · metamorphic tier: deterministic no licence file found · pointer only · 0ec8b081015d6151 · report fixture: returned Text_Encoder · level recorded 2026-09-22
Up in 24 papers src/networks/wordepth.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · ca0383a1bf504494 · report fixture: returned Up · level recorded 2026-09-22
_load_checkpoint src/networks/wordepth.py ran · our draft was wrong no licence file found · pointer only · 51d3a176d1206333 · report fixture: signature filename:str/0/str, map_location:NoneType/0/? · returned dict · level recorded 2026-09-22
compute_errors in 41 papers src/utils.py ran · honoured contract no licence file found · pointer only · e87fd998291bd040 · report fixture: signature gt:ndarray/1/float, pred:ndarray/1/float · returned list · level recorded 2026-09-24
get_dist_info in 5 papers src/networks/wordepth.py ran · metamorphic tier: well formed no licence file found · pointer only · a91567db5e6c35b4 · report fixture: returned tuple · level recorded 2026-09-22
get_num_lines in 10 papers src/utils.py ran · honoured contract no licence file found · pointer only · 050c56fb7282eb88 · report fixture: signature file_path:str/0/str · returned int · level recorded 2026-09-22
get_torchvision_models src/networks/wordepth.py ran · metamorphic tier: deterministic no licence file found · pointer only · a1b8bb2acb22a0ec · report fixture: returned dict · level recorded 2026-09-22
normalize_result in 6 papers src/utils.py ran no licence file found · pointer only · 8a05ea4d5e917bf4 · report fixture: signature value:Tensor/3/float, vmin:NoneType/0/?, vmax:NoneType/0/? · returned ndarray · level recorded 2026-09-24
preprocessing_transforms in 9 papers src/dataloaders/dataloader.py ran · our draft was wrong no licence file found · pointer only · 46c295513e59ec5a · report fixture: signature mode:str/0/str · returned Compose · level recorded 2026-09-24
window_reverse in 296 papers src/networks/swin_transformer.py ran · our draft was wrong no licence file found · pointer only · 61bf152e6a42a184 · report fixture: signature windows:Tensor/4/float, window_size:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded, date not recorded
BasicLayer in 56 papers src/networks/wordepth.py unverified no licence file found · pointer only · 4474d70757f8bbdf · report
DoubleConv in 23 papers
census: 8 implementations from 7 papers, 6 distinct outputs on one shared input
src/networks/wordepth.py unverified no licence file found · pointer only · 533554e0f3ae3b96 · report
SwinTransformer in 15 papers src/networks/wordepth.py unverified no licence file found · pointer only · 0ba2498ffe0b4454 · report
WorDepth src/networks/wordepth.py unverified no licence file found · pointer only · 895009095cba7a32 · report
is_module_wrapper in 8 papers src/networks/wordepth.py unverified no licence file found · pointer only · 9b9dd29ad0d626a0 · report
load_checkpoint in 277 papers src/networks/wordepth.py unverified no licence file found · pointer only · 99a1fadf82ab1b67 · report
load_state_dict in 114 papers src/networks/wordepth.py unverified no licence file found · pointer only · b9bb350524a8fa9f · report
load_url_dist in 7 papers src/networks/wordepth.py unverified no licence file found · pointer only · 3b1a511338023426 · report
load_url_dist in 7 papers src/networks/utils.py unverified no licence file found · pointer only · 92dad73ee855852f · 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 WorDepth (graph method: WorDepth). 25 bricks; individually on a fixture: 16 ran (of which 10 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

  1. WorDepth entry · level 0 · unverified · 895009095cba7a32
  2. EpsLayer model · level 1 · ran · 78636f3e5d41d22f
  3. MetricLayer model · level 1 · ran · e42969b7bf86747e
  4. OutConv model · level 1 · ran · 96be5d7e36e0d6f8
  5. Refine model · level 1 · ran · 22c1941ae236e18b
  6. SILogLoss loss · level 1 · ran · f78085ec460691c1
  7. SwinTransformer helper · level 0 · unverified · 0ba2498ffe0b4454
  8. Text_Encoder model · level 1 · ran · 0ec8b081015d6151
  9. Up model · level 1 · ran · ca0383a1bf504494
  10. BasicLayer helper · level 0 · unverified · 4474d70757f8bbdf
  11. PatchEmbed helper · level 1 · ran · 119f41dde4cc5c1b
  12. PatchMerging helper · level 1 · ran · be586c7612ce6beb
  13. load_checkpoint helper · level 0 · unverified · 99a1fadf82ab1b67
  14. DoubleConv model · level 0 · unverified · 533554e0f3ae3b96
  15. SwinTransformerBlock helper · level 0 · unverified · a1aa4e604c6c304d
  16. window_partition helper · level 2 · ran; the contract check could not run (RAISES) · 144d10b49baeb8a6
  17. _load_checkpoint helper · level 1 · ran · our draft was wrong · 51d3a176d1206333
  18. load_state_dict helper · level 0 · unverified · b9bb350524a8fa9f
  19. Mlp helper · level 1 · ran · ab49e7dfb4c6af7e
  20. WindowAttention helper · level 1 · ran · e72484de5dddeb6b
  21. window_reverse helper · level 1 · ran · our draft was wrong · 61bf152e6a42a184
  22. get_torchvision_models helper · level 1 · ran · a1b8bb2acb22a0ec
  23. load_url_dist helper · level 0 · unverified · 3b1a511338023426
  24. get_dist_info helper · level 1 · ran · a91567db5e6c35b4
  25. 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="2404.03635") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D ReconstructionDepth 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