Papers › Geometry Uncertainty Projection Network for Monocular 3D Object Detection

Geometry Uncertainty Projection Network for Monocular 3D Object Detection

29 Jul 2021ICCV 2021 10arXiv:2107.13774archive 2025-07-28

Yan Lu, Xinzhu Ma, Lei Yang, Tianzhu Zhang, Yating Liu, Qi Chu, Junjie Yan, Wanli Ouyang

Geometry Projection is a powerful depth estimation method in monocular 3D object detection. It estimates depth dependent on heights, which introduces mathematical priors into the deep model. But projection process also introduces the error amplification problem, in which the error of the estimated height will be amplified and reflected greatly at the output depth. This property leads to uncontrollable depth inferences and also damages the training efficiency. In this paper, we propose a Geometry Uncertainty Projection Network (GUP Net) to tackle the error amplification problem at both inference and training stages. Specifically, a GUP module is proposed to obtains the geometry-guided uncertainty of the inferred depth, which not only provides high reliable confidence for each depth but also benefits depth learning. Furthermore, at the training stage, we propose a Hierarchical Task Learning strategy to reduce the instability caused by error amplification. This learning algorithm monitors the learning situation of each task by a proposed indicator and adaptively assigns the proper loss weights for different tasks according to their pre-tasks situation. Based on that, each task starts learning only when its pre-tasks are learned well, which can significantly improve the stability and efficiency of the training process. Extensive experiments demonstrate the effectiveness of the proposed method. The overall model can infer more reliable object depth than existing methods and outperforms the state-of-the-art image-based monocular 3D detectors by 3.74% and 4.7% AP40 of the car and pedestrian categories on the KITTI benchmark.

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 21 code samples harvested from 1 repository linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 21 samples from 1 repository, 16 ran (10 with no instrument failure; 6 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 16 samples that ran has no recorded date.

supermhp/gupnet officialmentioned in paperpytorchMITSyntology: 21 samples, 16 ran (6 instrument-failed) · 5 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

21 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 5 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.

1ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
3ran; the contract check could not run
8ran
5unverified

Licence: 2 of the 21 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from supermhp/gupnet. “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.

supermhp/gupnet official repository 21 samples, 16 ran (6 instrument-failed) · 5 unverified
_gather_feat code/lib/models/gupnet.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 96f6547d6d3a3fce · report fixture: signature feat:Tensor/3/float, ind:Tensor/2/int, mask:Tensor/2/bool · returned Tensor · level recorded 2026-09-22
_nms code/lib/models/gupnet.py ran · our draft was wrong fingerprinted MIT (permissive) · 9cc3c87feb179eff · report fixture: signature heatmap:Tensor/4/float, kernel:int/0/int · returned Tensor · level recorded 2026-09-22
_transpose_and_gather_feat code/lib/models/gupnet.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 062a3f34484aa5ae · report fixture: signature feat:Tensor/4/float, ind:Tensor/2/int · returned Tensor · level recorded 2026-09-22
angle2class in 6 papers code/lib/datasets/utils.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · 39dc7b17b3bf3218 · report fixture: signature angle:float/0/float · returned tuple · level recorded 2026-09-24
build_optimizer in 83 papers code/lib/helpers/optimizer_helper.py ran MIT (permissive) · d7531c865af9dac9 · report fixture: signature cfg_optimizer:dict/0/?, model:callable/0/? · returned Adam · level recorded 2026-09-25
check_range in 5 papers code/lib/datasets/utils.py ran fingerprinted MIT (permissive) · e2619cecce6ca5d5 · report fixture: signature angle:float/0/float · returned float · level recorded 2026-09-25
conv3x3 in 1,376 papers code/lib/backbones/dla.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · fac5364e2f53c6db · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
conv3x3 in 1,376 papers code/lib/backbones/resnet.py ran MIT (permissive) · c875390a9fab8007 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-25
extract_input_from_tensor code/lib/models/gupnet.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · f6907c844231eed4 · report fixture: signature input:Tensor/4/float, ind:Tensor/2/int, mask:Tensor/2/bool · returned Tensor · level recorded 2026-09-22
get_angle_from_box3d code/lib/datasets/utils.py ran MIT (permissive) · ea47cdbdb36b7bc7 · report fixture: signature box3d_pts_3d:list/1/ndarray · returned float64 · level recorded 2026-09-25
get_calib_from_file in 7 papers code/lib/datasets/kitti_utils.py ran MIT (permissive) · ebd8a3fc2a270133 · report fixture: signature calib_file:str/0/str · returned dict · level recorded 2026-09-25
get_dir in 14 papers code/lib/datasets/kitti_utils.py ran · violated contract fingerprinted MIT (permissive) · 5d546e1ecbee1866 · report fixture: signature src_point:list/1/float, rot_rad:float/0/float · returned list · level recorded 2026-09-22
get_model_url in 11 papers code/lib/backbones/dla.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
get_objects_from_label code/lib/datasets/kitti_utils.py ran MIT (permissive) · 8274533a00c7a30a · report fixture: signature label_file:str/0/str · returned list · level recorded 2026-09-25
resnet18 in 432 papers code/lib/backbones/resnet.py ran MIT (permissive) · a2df86776904df7a · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-25
resnet34 in 148 papers code/lib/backbones/resnet.py ran MIT (permissive) · 03238865f53f8f40 · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-25
GUPNet code/lib/models/gupnet.py unverified MIT (permissive) · 0e9f041e43897d96 · report
_topk code/lib/models/gupnet.py unverified MIT (permissive) · 026b32da103167e6 · report
dla34 in 5 papers code/lib/backbones/dla.py unverified MIT (permissive) · 1e380a5690a619ef · report
extract_dets_from_outputs code/lib/helpers/decode_helper.py unverified MIT (permissive) · 615edfe53f0e9355 · report
weights_init_xavier code/lib/models/gupnet.py unverified MIT (permissive) · cb4724b9596507d8 · 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 Geometry Uncertainty Projection Network (GUP Net) (graph method: Geometry Uncertainty Projection Network (GUP Net)). 7 bricks; individually on a fixture: 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. GUPNet entry · level 0 · unverified · 0e9f041e43897d96
  2. _nms helper · level 1 · ran · our draft was wrong · 9cc3c87feb179eff
  3. _topk helper · level 0 · unverified · 026b32da103167e6
  4. extract_input_from_tensor helper · level 1 · ran; the contract check could not run (RAISES) · f6907c844231eed4
  5. weights_init_xavier helper · level 0 · unverified · cb4724b9596507d8
  6. _gather_feat helper · level 1 · ran; the contract check could not run (RAISES) · 96f6547d6d3a3fce
  7. _transpose_and_gather_feat helper · level 1 · ran; the contract check could not run (RAISES) · 062a3f34484aa5ae

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="2107.13774") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D Object Detection3D Object Detection From Monocular ImagesDepth EstimationMonocular 3D Object DetectionObjectObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection From Monocular Images KITTI-360 GUPNet AP25 27.25 #7 of 11 Archive leaderboard report
3D Object Detection From Monocular Images KITTI-360 GUPNet AP50 0.87 #7 of 11 Archive leaderboard report
3D Object Detection From Monocular Images Waymo Open Dataset GUP Net 3D mAPH Vehicle (Front Camera Only) 2.14 #2 of 3 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