Papers › Center-based 3D Object Detection and Tracking

Center-based 3D Object Detection and Tracking

19 Jun 2020CVPR 2021 1arXiv:2006.11275archive 2025-07-28

Tianwei Yin, Xingyi Zhou, Philipp Krähenbühl

Three-dimensional objects are commonly represented as 3D boxes in a point-cloud. This representation mimics the well-studied image-based 2D bounding-box detection but comes with additional challenges. Objects in a 3D world do not follow any particular orientation, and box-based detectors have difficulties enumerating all orientations or fitting an axis-aligned bounding box to rotated objects. In this paper, we instead propose to represent, detect, and track 3D objects as points. Our framework, CenterPoint, first detects centers of objects using a keypoint detector and regresses to other attributes, including 3D size, 3D orientation, and velocity. In a second stage, it refines these estimates using additional point features on the object. In CenterPoint, 3D object tracking simplifies to greedy closest-point matching. The resulting detection and tracking algorithm is simple, efficient, and effective. CenterPoint achieved state-of-the-art performance on the nuScenes benchmark for both 3D detection and tracking, with 65.5 NDS and 63.8 AMOTA for a single model. On the Waymo Open Dataset, CenterPoint outperforms all previous single model method by a large margin and ranks first among all Lidar-only submissions. The code and pretrained models are available at https://github.com/tianweiy/CenterPoint.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2006.11275")

Code

Syntology Ran 7 of 22 code samples harvested from 3 repositories linked to this paper; 15 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 2 ran · fixture could not drive it; 4 ran with no contract checked.

By repository: community (archive-listed): 22 samples from 3 repositories, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

13 repositories listed; official and paper-mentioned ones first.

tianweiy/CenterPoint officialmentioned in papermentioned on GitHubpytorchMIT report
15526837635/CenterPoint mentioned on GitHubpytorchMIT report
CarkusL/CenterPoint mentioned on GitHubpytorchMIT report
abhigoku10/CenterPoint_PC mentioned on GitHubpytorchMIT report
chowkamlee81/CentrePointNet mentioned on GitHubpytorchMIT report
livox-sdk/livox_detection mentioned on GitHubpytorch report
mon95/centerpoint-maps mentioned on GitHubpytorchMIT report
nvidia-ai-iot/lidar_ai_solution mentioned on GitHubpytorchNOASSERTION report
safetylab24/FusionCVCP mentioned on GitHubpytorchMIT report
tianweiy/CenterPoint-KITTI mentioned on GitHubpytorchApache-2.0 report
PaddlePaddle/Paddle3D paddleApache-2.0 report
open-mmlab/mmdetection3d pytorchApache-2.0 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

22 samples harvested; 7 ran; 0 honoured the contract we drafted; 15 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
2ran · fixture could not drive it
4ran
15unverified

Licence: 0 of the 22 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 3 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

check_numpy_to_torch livox-sdk/livox_detection/tools/test_ros.py community (archive-listed) ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 5c4bac81583c34e1 · report
cls_type_to_id tianweiy/CenterPoint-KITTI/pcdet/utils/object3d_kitti.py community (archive-listed) ran fingerprinted Apache-2.0 (permissive) · 68d59bd1b88d6e20 · report
div_up tianweiy/CenterPoint-KITTI/pcdet/datasets/kitti/kitti_object_eval_python/rotate_iou.py community (archive-listed) ran fingerprinted Apache-2.0 (permissive) · 20fbfa2279e1ce4b · report
gaussian_2d tianweiy/CenterPoint-KITTI/pcdet/models/dense_heads/centerpoint_head_single.py community (archive-listed) ran Apache-2.0 (permissive) · ea036153b550642a · report
get_image_index_str tianweiy/CenterPoint-KITTI/pcdet/datasets/kitti/kitti_object_eval_python/kitti_common.py community (archive-listed) ran fingerprinted Apache-2.0 (permissive) · 3415a0d1c950c1c7 · report
mask_points_out_of_range livox-sdk/livox_detection/tools/test_ros.py community (archive-listed) ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · b17bee95672f577a · report
rotate_points_along_z livox-sdk/livox_detection/tools/test_ros.py community (archive-listed) ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · df17a2b345c6cccd · report
cfg_from_yaml_file tianweiy/CenterPoint-KITTI/pcdet/config.py community (archive-listed) unverified Apache-2.0 (permissive) · 696fe155f9990d38 · report
clip_sigmoid tianweiy/CenterPoint-KITTI/pcdet/models/dense_heads/centerpoint_head_single.py community (archive-listed) unverified Apache-2.0 (permissive) · 2910537cc2d708f3 · report
flip zion-king/Center-based-3D-Object-Detection-and-Tracking/det3d/core/utils/center_utils.py community (archive-listed) unverified MIT (permissive) · 71c86b456fb1f8d8 · report
get_affine_transform zion-king/Center-based-3D-Object-Detection-and-Tracking/det3d/core/utils/center_utils.py community (archive-listed) unverified MIT (permissive) · da4199bc7189c53d · report
get_calib_from_file tianweiy/CenterPoint-KITTI/pcdet/utils/calibration_kitti.py community (archive-listed) unverified Apache-2.0 (permissive) · ebd8a3fc2a270133 · report
get_corner_loss_lidar tianweiy/CenterPoint-KITTI/pcdet/utils/loss_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 1780d388cc532a6d · report
get_image_path tianweiy/CenterPoint-KITTI/pcdet/datasets/kitti/kitti_object_eval_python/kitti_common.py community (archive-listed) unverified Apache-2.0 (permissive) · c8b847449b3be5dc · report
get_kitti_info_path tianweiy/CenterPoint-KITTI/pcdet/datasets/kitti/kitti_object_eval_python/kitti_common.py community (archive-listed) unverified Apache-2.0 (permissive) · f027b5ae160547ce · report
get_objects_from_label tianweiy/CenterPoint-KITTI/pcdet/utils/object3d_kitti.py community (archive-listed) unverified Apache-2.0 (permissive) · 4ebc0d049adc6eac · report
inverse_sigma zion-king/Center-based-3D-Object-Detection-and-Tracking/det3d/datasets/utils/ground_plane_detection.py community (archive-listed) unverified MIT (permissive) · 363a2d53034b488a · report
merge_new_config tianweiy/CenterPoint-KITTI/pcdet/config.py community (archive-listed) unverified Apache-2.0 (permissive) · 392c0cf3a1b07b12 · report
multi_apply tianweiy/CenterPoint-KITTI/pcdet/models/dense_heads/centerpoint_head_single.py community (archive-listed) unverified Apache-2.0 (permissive) · 77ab54971d45f552 · report
svd zion-king/Center-based-3D-Object-Detection-and-Tracking/det3d/datasets/utils/ground_plane_detection.py community (archive-listed) unverified MIT (permissive) · 0215535ccf00014e · report
svd_solve zion-king/Center-based-3D-Object-Detection-and-Tracking/det3d/datasets/utils/ground_plane_detection.py community (archive-listed) unverified MIT (permissive) · d9f32b1e24612346 · report
transform_preds zion-king/Center-based-3D-Object-Detection-and-Tracking/det3d/core/utils/center_utils.py community (archive-listed) unverified MIT (permissive) · fcb93febe125336c · report

Tasks

3D Multi-Object Tracking3D Object Detection3D Object Tracking3D Pedestrian TrackingObjectObject DetectionObject TrackingRobust 3D Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Multi-Object Tracking nuScenes CenterPoint-Single AMOTA 0.64 #50 of 115 Archive leaderboard report
3D Object Detection ONCE CenterPoint mAP 60.1 #2 of 2 Archive leaderboard report
3D Object Detection Waymo Open Dataset CenterPoint mAPH/L2 65.8 #8 of 8 Archive leaderboard report
3D Object Detection nuScenes CenterPoint NDS 0.71 #78 of 372 Archive leaderboard report
3D Object Detection nuScenes CenterPoint mAAE 0.14 #78 of 372 Archive leaderboard report
3D Object Detection nuScenes CenterPoint mAOE 0.35 #78 of 372 Archive leaderboard report
3D Object Detection nuScenes CenterPoint mAP 0.67 #78 of 372 Archive leaderboard report
3D Object Detection nuScenes CenterPoint mASE 0.24 #78 of 372 Archive leaderboard report
3D Object Detection nuScenes CenterPoint mATE 0.25 #78 of 372 Archive leaderboard report
3D Object Detection nuScenes CenterPoint mAVE 0.25 #78 of 372 Archive leaderboard report
3D Object Detection nuScenes LiDAR only CenterPoint NDS 67.3 #5 of 7 Archive leaderboard report
3D Object Detection nuScenes LiDAR only CenterPoint NDS (val) 66.8 #5 of 7 Archive leaderboard report
3D Object Detection nuScenes LiDAR only CenterPoint mAP 60.3 #5 of 7 Archive leaderboard report
3D Object Detection nuScenes LiDAR only CenterPoint mAP (val) 59.6 #5 of 7 Archive leaderboard report
3D Object Detection waymo all_ns CenterPoint APH/L2 71.93 #1 of 2 Archive leaderboard report
3D Object Detection waymo cyclist CenterPoint APH/L2 71.28 #4 of 7 Archive leaderboard report
3D Object Detection waymo pedestrian CenterPoint APH/L2 71.52 #5 of 7 Archive leaderboard report
3D Pedestrian Tracking nuScenes validation set Center-based Tracking AMOTA 77.3 #2 of 4 Archive leaderboard report
Robust 3D Object Detection KITTI-C CenterPoint mean Corruption Error (mCE) 100.00% #4 of 5 Archive leaderboard report
Robust 3D Object Detection nuScenes-C CenterPoint-PP mean Corruption Error (mCE) 100.00 #1 of 1 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