Papers › FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection

FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection

22 Apr 2021arXiv:2104.10956archive 2025-07-28

Tai Wang, Xinge Zhu, Jiangmiao Pang, Dahua Lin

Monocular 3D object detection is an important task for autonomous driving considering its advantage of low cost. It is much more challenging than conventional 2D cases due to its inherent ill-posed property, which is mainly reflected in the lack of depth information. Recent progress on 2D detection offers opportunities to better solving this problem. However, it is non-trivial to make a general adapted 2D detector work in this 3D task. In this paper, we study this problem with a practice built on a fully convolutional single-stage detector and propose a general framework FCOS3D. Specifically, we first transform the commonly defined 7-DoF 3D targets to the image domain and decouple them as 2D and 3D attributes. Then the objects are distributed to different feature levels with consideration of their 2D scales and assigned only according to the projected 3D-center for the training procedure. Furthermore, the center-ness is redefined with a 2D Gaussian distribution based on the 3D-center to fit the 3D target formulation. All of these make this framework simple yet effective, getting rid of any 2D detection or 2D-3D correspondence priors. Our solution achieves 1st place out of all the vision-only methods in the nuScenes 3D detection challenge of NeurIPS 2020. Code and models are released at https://github.com/open-mmlab/mmdetection3d.

PaperPDFCodeCode Syntology ran

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

No sample from the archive's official repository (open-mmlab/mmdetection3d) is linked to this paper; the 22 samples below come from 4 community repositories. Syntology harvested code from open-mmlab/mmdetection3d for another paper.

open-mmlab/mmdetection3d: Syntology's graph links these samples to An Empirical Study of Training State-of-the-Art LiDAR Segmentation Models (arXiv:2405.14870; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method.

Syntology 22 code samples harvested from 4 repositories linked to this paper: 20 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 1 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 2 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: community (archive-listed): 22 samples from 4 repositories, 20 ran (14 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.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

open-mmlab/mmdetection3d officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An Empirical Study of Training State-of-the-Art LiDAR Segmentation Models (arXiv:2405.14870; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
AllenPeng0209/deeproute_competition mentioned on GitHubpytorchApache-2.0Syntology: 7 samples, 6 ran (2 instrument-failed) · 1 unverified report
Discover304/MMDetection3D-Eloss mentioned on GitHubpytorchApache-2.0Syntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
bosszhe/vimi mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to VIMI: Vehicle-Infrastructure Multi-view Intermediate Fusion for Camera-based 3D Object... (arXiv:2303.10975; that paper's own run record: 2 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; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
jhkim-spa/FVNet_v2 mentioned on GitHubpytorchApache-2.0Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
konyul/mmdet3d mentioned on GitHubpytorchApache-2.0Syntology: 12 samples, 11 ran (4 instrument-failed) · 1 unverified report
vision-agh/pointpillars-backbone mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
vision-agh/pointpillars_backbone mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
yhbcode000/MMDetection3D-Eloss mentioned on GitHubpytorchApache-2.0Syntology: 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

22 samples harvested: 20 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 1 violated, 11 with no contract checked; 6 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 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
1ran · violated contract
3ran · our draft was wrong
3ran; the contract check could not run
11ran
2unverified

Licence: 7 of the 22 samples are pointer only, meaning Syntology does not serve that copy's text. For 7 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 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

AllenPeng0209/deeproute_competition community (archive-listed) 7 samples, 6 ran (2 instrument-failed) · 1 unverified
clean_data in 13 papers mmdet3d/core/evaluation/deeproute_utils/deeproute_eval.py ran Apache-2.0 (permissive) · 853d5d97b4442543 · report fixture: signature gt_anno:dict/0/?, dt_anno:dict/0/?, current_class:int/0/int, difficulty:int/0/int, difficulty_metric:NoneType/0/? · returned tuple · level recorded 2026-09-24
div_up in 10 papers mmdet3d/core/evaluation/deeproute_utils/rotate_iou.py ran fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 20fbfa2279e1ce4b · report fixture: signature m:int/0/int, n:int/0/int · returned int · level recorded 2026-09-24
get_model_dataset in 28 papers .dev_scripts/gather_models.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · da059252c88ecf40 · report fixture: signature log_json_path:str/0/str · returned str · level recorded 2026-09-26
get_thresholds in 7 papers mmdet3d/core/evaluation/deeproute_utils/deeproute_eval.py ran Apache-2.0 (permissive) · 89ab5b12e60b6dc2 · report fixture: signature scores:ndarray/1/float, num_gt:int/0/int, num_sample_pts:int/0/int · returned list · level recorded 2026-09-24
image_box_overlap mmdet3d/core/evaluation/deeproute_utils/deeproute_eval.py ran fingerprinted Apache-2.0 (permissive) · 7131430b63714f53 · report fixture: signature boxes:ndarray/2/float, query_boxes:ndarray/2/float, criterion:int/0/int · returned ndarray · level recorded 2026-09-24
process_checkpoint in 87 papers .dev_scripts/gather_models.py ran · our draft was wrong Apache-2.0 (permissive) · e76a491553cf9fcf · report fixture: signature in_file:str/0/str, out_file:str/0/str · returned str · level recorded 2026-09-24
get_final_epoch in 36 papers .dev_scripts/gather_models.py unverified Apache-2.0 (permissive) · 90f6ae7209cde36f · report
Discover304/MMDetection3D-Eloss community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
calculate_entropy in 22 papers mmdet3d/models/losses/eloss.py ran Apache-2.0 (permissive) · 356e77e178d28771 · report fixture: signature feats:Tensor/4/float, k:int/0/int · returned Tensor · level recorded 2026-09-24
pairwise_euclidean_distance mmdet3d/models/losses/eloss.py ran fingerprinted Apache-2.0 (permissive) · 3b15102fec2dd1c2 · report fixture: signature x:Tensor/2/float, y:Tensor/2/float · returned Tensor · level recorded 2026-09-24
jhkim-spa/FVNet_v2 community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
get_final_epoch in 36 papers .dev_scripts/gather_models.py ran fingerprinted Apache-2.0 (permissive) · 6434c4b76548f533 · report fixture: signature config:str/0/str · returned int · level recorded 2026-09-24
konyul/mmdet3d community (archive-listed) 12 samples, 11 ran (4 instrument-failed) · 1 unverified
average_precision in 38 papers mmdet3d/core/evaluation/indoor_eval.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) here; the stored copy is pointer only · 8d35a41368d8dd47 · report fixture: signature recalls:ndarray/2/float, precisions:ndarray/2/float, mode:str/0/str · returned ndarray · level recorded 2026-09-24
bbox3d2result in 5 papers mmdet3d/core/bbox/transforms.py ran Apache-2.0 (permissive) · 049f10575d6acf59 · report fixture: signature bboxes:Tensor/2/float, scores:Tensor/1/float, labels:Tensor/1/int, attrs:Tensor/1/int · returned dict · level recorded 2026-09-25
bbox3d2roi in 5 papers mmdet3d/core/bbox/transforms.py ran · honoured contract Apache-2.0 (permissive) · 071c297bbb04127e · report fixture: signature bbox_list:list/1/Tensor · returned Tensor · level recorded 2026-09-25
bbox3d_mapping_back in 5 papers mmdet3d/core/bbox/transforms.py ran Apache-2.0 (permissive) · cd7847cc58eb29bd · report fixture: signature bboxes:BaseInstance3DBoxes/0/?, scale_factor:float/0/float, flip_horizontal:bool/0/bool, flip_vertical:bool/0/bool · returned BaseInstance3DBoxes · level recorded 2026-09-25
box_camera_to_lidar in 10 papers mmdet3d/core/bbox/box_np_ops.py ran Apache-2.0 (permissive) · 96c8084488bd023b · report fixture: signature data:ndarray/2/float, r_rect:ndarray/2/float, velo2cam:ndarray/2/float · returned ndarray · level recorded 2026-09-25
camera_to_lidar in 10 papers mmdet3d/core/bbox/box_np_ops.py ran Apache-2.0 (permissive) · 9e22984820c39868 · report fixture: signature points:ndarray/2/float, r_rect:ndarray/2/float, velo2cam:ndarray/2/float · returned ndarray · level recorded 2026-09-25
corners_nd in 9 papers mmdet3d/core/bbox/box_np_ops.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 5b1dacd1f125c08f · report fixture: signature dims:ndarray/2/float, origin:float/0/float · returned ndarray · level recorded 2026-09-25
eval_det_cls in 6 papers mmdet3d/core/evaluation/indoor_eval.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 2283234eb1863906 · report fixture: signature pred:dict/0/?, gt:dict/0/?, iou_thr:list/1/float · returned list · level recorded 2026-09-24
fast_hist in 24 papers
census: 2 implementations from 6 papers, 1 distinct output on one shared input
mmdet3d/core/evaluation/seg_eval.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) here; the stored copy is pointer only · 7f5f5b45cabc7d55 · report fixture: signature preds:ndarray/1/int, labels:ndarray/1/int, num_classes:int/0/int · returned ndarray · level recorded 2026-09-24
get_acc in 22 papers mmdet3d/core/evaluation/seg_eval.py ran · honoured contract Apache-2.0 (permissive) here; the stored copy is pointer only · fcd32f0316ac7cac · report fixture: signature hist:ndarray/2/float · returned float32 · level recorded 2026-09-24
per_class_iou mmdet3d/core/evaluation/seg_eval.py ran · violated contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 4018d47e1ea5a2ce · report fixture: signature hist:ndarray/2/float · returned ndarray · level recorded 2026-09-24
eval_map_recall in 6 papers mmdet3d/core/evaluation/indoor_eval.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 3e68c67f05177852 · report

Tasks

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

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection nuScenes FCOS3D NDS 0.428 #327 of 372 Archive leaderboard report
3D Object Detection nuScenes FCOS3D mAAE 0.124 #327 of 372 Archive leaderboard report
3D Object Detection nuScenes FCOS3D mAOE 0.452 #327 of 372 Archive leaderboard report
3D Object Detection nuScenes FCOS3D mAP 0.358 #327 of 372 Archive leaderboard report
3D Object Detection nuScenes FCOS3D mASE 0.249 #327 of 372 Archive leaderboard report
3D Object Detection nuScenes FCOS3D mATE 0.690 #327 of 372 Archive leaderboard report
3D Object Detection nuScenes FCOS3D mAVE 1.434 #327 of 372 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