Papers › MonoWAD: Weather-Adaptive Diffusion Model for Robust Monocular 3D Object Detection

MonoWAD: Weather-Adaptive Diffusion Model for Robust Monocular 3D Object Detection

23 Jul 2024arXiv:2407.16448archive 2025-07-28

Youngmin Oh, Hyung-Il Kim, Seong Tae Kim, Jung Uk Kim

Monocular 3D object detection is an important challenging task in autonomous driving. Existing methods mainly focus on performing 3D detection in ideal weather conditions, characterized by scenarios with clear and optimal visibility. However, the challenge of autonomous driving requires the ability to handle changes in weather conditions, such as foggy weather, not just clear weather. We introduce MonoWAD, a novel weather-robust monocular 3D object detector with a weather-adaptive diffusion model. It contains two components: (1) the weather codebook to memorize the knowledge of the clear weather and generate a weather-reference feature for any input, and (2) the weather-adaptive diffusion model to enhance the feature representation of the input feature by incorporating a weather-reference feature. This serves an attention role in indicating how much improvement is needed for the input feature according to the weather conditions. To achieve this goal, we introduce a weather-adaptive enhancement loss to enhance the feature representation under both clear and foggy weather conditions. Extensive experiments under various weather conditions demonstrate that MonoWAD achieves weather-robust monocular 3D object detection. The code and dataset are released at https://github.com/VisualAIKHU/MonoWAD.

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 26 code samples harvested from 1 repository linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 26 samples from 1 repository, 15 ran (14 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.

visualaikhu/monowad officialmentioned in papermentioned on GitHubpytorchSyntology: 26 samples, 15 ran (1 instrument-failed) · 11 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: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 11 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 · our draft was wrong
14ran
11unverified

Licence: 0 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 visualaikhu/monowad. “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.

visualaikhu/monowad official repository 26 samples, 15 ran (1 instrument-failed) · 11 unverified
Attend in 6 papers visualDet3D/networks/detectors/MonoWAD.py ran fingerprinted MIT (permissive) · 360e36fe7ea92c19 · report fixture: signature q:Tensor/4/float, k:Tensor/4/float, v:Tensor/4/float · returned Tensor · level recorded 2026-09-24
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
visualDet3D/networks/detectors/MonoWAD.py ran · metamorphic tier: invariant MIT (permissive) · dfac04afda97fe38 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Bottleneck in 98 papers visualDet3D/networks/detectors/MonoWAD.py ran fingerprinted MIT (permissive) · f7f588495112f1d3 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
Conv2d in 43 papers
census: 7 implementations from 7 papers, 6 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
visualDet3D/networks/detectors/MonoWAD.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 9f54fd544c431a89 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
DLAUp visualDet3D/networks/detectors/MonoWAD.py ran MIT (permissive) · c3a2aeb5e289231e · report fixture: signature layers:list/1/Tensor · returned Tensor · level recorded 2026-09-24
DepthAwareFE visualDet3D/networks/detectors/MonoWAD.py ran MIT (permissive) · 4660642fa4ba3464 · report fixture: signature x:Tensor/4/float · returned tuple · level recorded 2026-09-24
IDAUp visualDet3D/networks/detectors/MonoWAD.py ran MIT (permissive) · f6dbf7aa2006b4ba · report fixture: returned list · level recorded 2026-09-24
LinearAttention in 20 papers visualDet3D/networks/detectors/MonoWAD.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · e483acb4ed97bccf · report fixture: signature queries:Tensor/4/float, keys:Tensor/4/float, values:Tensor/4/float · returned Tensor · level recorded 2026-09-22
RMSNorm in 61 papers visualDet3D/networks/detectors/MonoWAD.py ran · metamorphic tier: invariant MIT (permissive) · 234fd6dd12768c7d · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
RandomOrLearnedSinusoidalPosEmb visualDet3D/networks/detectors/MonoWAD.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 49db9b9ea5686382 · report fixture: signature x:Tensor/1/float · returned Tensor · level recorded 2026-09-22
TransDecoderLayer visualDet3D/networks/detectors/MonoWAD.py ran MIT (permissive) · 68df791593973dbe · report fixture: signature x:Tensor/3/float, source:Tensor/3/float · returned Tensor · level recorded 2026-09-24
TransEncoderLayer visualDet3D/networks/detectors/MonoWAD.py ran MIT (permissive) · 721c301e49b3f514 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
Tree in 10 papers visualDet3D/networks/detectors/MonoWAD.py ran fingerprinted MIT (permissive) · 8862f92d2180b857 · report fixture: signature x:Tensor/4/float, residual:NoneType/0/?, children:NoneType/0/? · returned Tensor · level recorded 2026-09-24
WeatherCodebook visualDet3D/networks/detectors/MonoWAD.py ran MIT (permissive) · a26331af1d2a725c · report fixture: returned tuple · level recorded 2026-09-24
get_model_url in 11 papers visualDet3D/networks/detectors/MonoWAD.py ran · our draft was wrong fingerprinted MIT (permissive) · 3c9867a84d7c18d9 · report fixture: signature data:str/0/str, name:str/0/str, hash:str/0/str · returned str · level recorded 2026-09-24
CrossAttention in 85 papers visualDet3D/networks/detectors/MonoWAD.py unverified MIT (permissive) · 056357c296407ea2 · report
DLA visualDet3D/networks/detectors/MonoWAD.py unverified MIT (permissive) · 66e5d28ac311f7fe · report
DepthAwarePosEnc visualDet3D/networks/detectors/MonoWAD.py unverified MIT (permissive) · 2f1466316451a519 · report
DepthAwareTransformer visualDet3D/networks/detectors/MonoWAD.py unverified MIT (permissive) · 1440222618f4b897 · report
GaussianDiffusion in 61 papers visualDet3D/networks/detectors/MonoWAD.py unverified MIT (permissive) · c41056f8a4f34abd · report
MonoWAD visualDet3D/networks/detectors/MonoWAD.py unverified MIT (permissive) · 64099da24b02e2be · report
Root visualDet3D/networks/detectors/MonoWAD.py unverified MIT (permissive) · 0aff889aa4679890 · report
Unet in 14 papers visualDet3D/networks/detectors/MonoWAD.py unverified MIT (permissive) · e275d60eaaba6a01 · report
dfe_module visualDet3D/networks/detectors/MonoWAD.py unverified MIT (permissive) · e28ea7c71f77af75 · report
dla102 visualDet3D/networks/detectors/MonoWAD.py unverified MIT (permissive) · f6223e37e1c97520 · 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 MonoWAD (graph method: MonoWAD). 45 bricks; individually on a fixture: 32 ran (of which 3 constructed an object rather than computing a result; 28 with no instrument failure: 8 honoured, 3 violated, 17 with no contract checked; 4 where Syntology's instrument failed) · 13 unverified. The assembly has not been run end-to-end.

  1. MonoWAD entry · level 0 · unverified · 64099da24b02e2be
  2. DLAUp helper · level 1 · ran · c3a2aeb5e289231e
  3. DepthAwareFE helper · level 1 · ran · 4660642fa4ba3464
  4. DepthAwarePosEnc helper · level 0 · unverified · 2f1466316451a519
  5. DepthAwareTransformer model · level 0 · unverified · 1440222618f4b897
  6. GaussianDiffusion model · level 0 · unverified · c41056f8a4f34abd
  7. Unet model · level 0 · unverified · e275d60eaaba6a01
  8. WeatherCodebook model · level 1 · ran · a26331af1d2a725c
  9. dla102 model · level 0 · unverified · f6223e37e1c97520
  10. IDAUp helper · level 1 · ran · f6dbf7aa2006b4ba
  11. dfe_module helper · level 0 · unverified · e28ea7c71f77af75
  12. TransDecoderLayer helper · level 1 · ran · 68df791593973dbe
  13. TransEncoderLayer helper · level 1 · ran · 721c301e49b3f514
  14. cosine_beta_schedule helper · level 1 · ran · honoured contract · 079814bd981435a5
  15. default helper · level 1 · ran · violated contract · d1ef6b8cb9a28a53
  16. extract helper · level 0 · unverified · 09c8479d9a5b3e06
  17. identity helper · level 2 · ran · honoured contract · 7f1040f5e3991d5e
  18. linear_beta_schedule helper · level 1 · ran · honoured contract · 6a00659c3eac0648
  19. normalize_to_neg_one_to_one helper · level 1 · ran · honoured contract · a1229a9f4df127e2
  20. sigmoid_beta_schedule helper · level 1 · ran · honoured contract · 42f0a0d13dfa897c
  21. unnormalize_to_zero_to_one helper · level 1 · ran · honoured contract · 97e1bbd232dfe092
  22. Attention helper · level 1 · ran · dfac04afda97fe38
  23. CrossAttention helper · level 0 · unverified · 056357c296407ea2
  24. Downsample helper · level 1 · ran · our draft was wrong · b5bf8353f4199efb
  25. LinearAttention helper · level 1 · ran · e483acb4ed97bccf
  26. RandomOrLearnedSinusoidalPosEmb helper · level 1 · ran · 49db9b9ea5686382
  27. ResnetBlock helper · level 1 · ran · b18e27ad640dde3d
  28. SinusoidalPosEmb helper · level 1 · ran · 3f9e9512b765d426
  29. Upsample helper · level 1 · ran · our draft was wrong · 410a7d2e8c88e682
  30. cast_tuple helper · level 1 · ran · honoured contract · d229662b12e581b6
  31. divisible_by helper · level 2 · ran · violated contract · 856d86b39c6005b4
  32. Bottleneck helper · level 1 · ran · f7f588495112f1d3
  33. DLA helper · level 0 · unverified · 66e5d28ac311f7fe
  34. Conv2d helper · level 1 · ran · 9f54fd544c431a89
  35. fill_up_weights helper · level 0 · unverified · 6782a16d92f19242
  36. exists helper · level 1 · ran · violated contract · 608e364a9d2376a3
  37. Attend helper · level 1 · ran · 360e36fe7ea92c19
  38. RMSNorm helper · level 1 · ran · 234fd6dd12768c7d
  39. elu_feature_map helper · level 1 · ran · honoured contract · 0d5505bd782b4a89
  40. Block helper · level 1 · ran · 1b1fcc6ab25fa4ef
  41. BasicBlock helper · level 0 · unverified · 822bbc27c98772b9
  42. Tree helper · level 1 · ran · 8862f92d2180b857
  43. get_model_url helper · level 1 · ran · our draft was wrong · 3c9867a84d7c18d9
  44. Root helper · level 0 · unverified · 0aff889aa4679890
  45. once helper · level 1 · ran · our draft was wrong · 52e10a7d6b0fa036

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="2407.16448") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D Object DetectionAutonomous DrivingDenoisingMonocular 3D Object DetectionObjectObject Detectionobject-detection

Datasets

Introduced by this paper, per the archive.

Foggy KITTI

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionDiffusionFocusSoftmax

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