Papers › Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection

Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection

26 Aug 2019arXiv:1908.09492archive 2025-07-28

Benjin Zhu, Zhengkai Jiang, Xiangxin Zhou, Zeming Li, Gang Yu

This report presents our method which wins the nuScenes3D Detection Challenge [17] held in Workshop on Autonomous Driving(WAD, CVPR 2019). Generally, we utilize sparse 3D convolution to extract rich semantic features, which are then fed into a class-balanced multi-head network to perform 3D object detection. To handle the severe class imbalance problem inherent in the autonomous driving scenarios, we design a class-balanced sampling and augmentation strategy to generate a more balanced data distribution. Furthermore, we propose a balanced group-ing head to boost the performance for the categories withsimilar shapes. Based on the Challenge results, our methodoutperforms the PointPillars [14] baseline by a large mar-gin across all metrics, achieving state-of-the-art detection performance on the nuScenes dataset. Code will be released at CBGS.

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

Syntology 22 code samples harvested from 2 repositories linked to this paper: 20 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 2 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: 10 samples from 1 repository, 9 ran (8 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 12 samples from 1 repository, 11 ran (11 with no instrument failure; 0 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 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

poodarchu/Class-balanced-Grouping-and-Sampling-for-Point-Cloud-3D-Object-Detection officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 10 samples, 9 ran (1 instrument-failed) · 1 unverified report
johnwlambert/argoverse_cbgs_kf_tracker mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Argoverse: 3D Tracking and Forecasting with Rich Maps (arXiv:1911.02620; that paper's own run record: 1 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; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
poodarchu/Det3D mentioned on GitHubpytorchApache-2.0Syntology: 12 samples, 11 ran (0 instrument-failed) · 1 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.

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; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 1 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.

1ran · our draft was wrong
19ran
2unverified

Licence: 1 of the 22 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 2 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.

poodarchu/Class-balanced-Grouping-and-Sampling-for-Point-Cloud-3D-Object-Detection official repository 10 samples, 9 ran (1 instrument-failed) · 1 unverified
bound_points_jit det3d/ops/point_cloud/point_cloud_ops.py ran Apache-2.0 (permissive) · e5993ab3f1529dc7 · report fixture: signature points:ndarray/2/float, upper_bound:ndarray/1/float, lower_bound:ndarray/1/float · returned ndarray · level recorded 2026-09-25
div_up in 10 papers det3d/datasets/utils/kitti_object_eval_python/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_image_index_str in 7 papers det3d/datasets/utils/kitti_object_eval_python/kitti_common.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 3415a0d1c950c1c7 · report fixture: signature img_idx:int/0/int · returned str · level recorded 2026-09-24
get_image_path in 15 papers det3d/datasets/utils/kitti_object_eval_python/kitti_common.py ran Apache-2.0 (permissive) · c8b847449b3be5dc · report fixture: signature idx:int/0/int, prefix:str/0/str, training:bool/0/bool, relative_path:bool/0/bool · returned str · level recorded 2026-09-25
inverse_sigma det3d/datasets/utils/ground_plane_detection.py ran Apache-2.0 (permissive) · 363a2d53034b488a · report fixture: signature S:MatrixLike/0/? · returned MatrixLike · level recorded 2026-09-25
points_to_bev det3d/ops/point_cloud/bev_ops.py ran Apache-2.0 (permissive) · 0a6df8e3e11be41b · report fixture: signature points:ndarray/2/float, voxel_size:list/1/float, coors_range:list/1/float, with_reflectivity:bool/0/bool, density_norm_num:int/0/int, max_voxels:int/0/int · returned ndarray · level recorded 2026-09-25
points_to_voxel det3d/ops/point_cloud/point_cloud_ops.py ran Apache-2.0 (permissive) · 7ce4e5103722da22 · report fixture: signature points:ndarray/2/float, voxel_size:ndarray/1/float, coors_range:ndarray/1/float, max_points:int/0/int, reverse_index:bool/0/bool, max_voxels:int/0/int · returned tuple · level recorded 2026-09-25
svd in 12 papers det3d/datasets/utils/ground_plane_detection.py ran fingerprinted Apache-2.0 (permissive) · 0215535ccf00014e · report fixture: signature A:ndarray/2/float · returned tuple · level recorded 2026-09-25
svd_solve det3d/datasets/utils/ground_plane_detection.py ran fingerprinted Apache-2.0 (permissive) · d9f32b1e24612346 · report fixture: signature A:ndarray/2/float, b:ndarray/1/float · returned ndarray · level recorded 2026-09-25
get_kitti_info_path in 7 papers det3d/datasets/utils/kitti_object_eval_python/kitti_common.py unverified Apache-2.0 (permissive) · f027b5ae160547ce · report
poodarchu/Det3D community (archive-listed) 12 samples, 11 ran (0 instrument-failed) · 1 unverified
bbox_overlaps in 20 papers det3d/core/bbox/iou.py ran Apache-2.0 (permissive) · 93aa32a1463f1fad · report fixture: signature bboxes1:Tensor/2/float, bboxes2:Tensor/2/float, mode:str/0/str, is_aligned:bool/0/bool · returned Tensor · level recorded 2026-09-24
create_target_np in 5 papers det3d/core/anchor/target_ops.py ran Apache-2.0 (permissive) · 20f05c72a0b0b39d · report fixture: signature all_anchors:ndarray/2/float, gt_boxes:ndarray/2/float, similarity_fn:callable/0/?, box_encoding_fn:callable/0/?, prune_anchor_fn:callable/0/?, gt_classes:ndarray/1/int, matched_threshold:float/0/float, unmatched_threshold:float/0/float, bbox_inside_weight:NoneType/0/?, positive_fraction:float/0/float, rpn_batch_size:int/0/int, norm_by_num_examples:bool/0/bool, box_code_size:int/0/int · returned dict · level recorded 2026-09-24
is_line_segment_intersection_jit det3d/core/bbox/geometry.py ran Apache-2.0 (permissive) · 0513b9d43a6d7883 · report fixture: signature lines1:ndarray/3/float, lines2:ndarray/3/float · returned ndarray · level recorded 2026-09-24
line_segment_intersection det3d/core/bbox/geometry.py ran Apache-2.0 (permissive) · 6a7ad14559c54076 · report fixture: signature line1:ndarray/2/float, line2:ndarray/2/float, intersection:ndarray/1/float · returned bool · level recorded 2026-09-25
make_dot in 11 papers det3d/visualization/netviz.py ran Apache-2.0 (permissive) · 78f63746495b109f · report fixture: signature var:Tensor/0/float, params:dict/0/? · returned Digraph · level recorded 2026-09-24
points_count_convex_polygon_3d_jit det3d/core/bbox/geometry.py ran Apache-2.0 (permissive) · 0dba4924dbd3544f · report fixture: signature points:ndarray/2/float, polygon_surfaces:ndarray/4/float, num_surfaces:ndarray/1/int · returned ndarray · level recorded 2026-09-24
replace in 8 papers det3d/visualization/netviz.py ran Apache-2.0 (permissive) · 34a445a4ab172be6 · report fixture: signature name:str/0/str, scope:dict/0/? · returned str · level recorded 2026-09-24
second_box_decode det3d/core/bbox/box_torch_ops.py ran Apache-2.0 (permissive) · 755dd896938eee95 · report fixture: signature box_encodings:Tensor/2/float, anchors:Tensor/2/float, encode_angle_to_vector:bool/0/bool, bin_loss:bool/0/bool, smooth_dim:bool/0/bool, norm_velo:bool/0/bool · returned Tensor · level recorded 2026-09-24
second_box_encode in 5 papers det3d/core/bbox/box_torch_ops.py ran Apache-2.0 (permissive) · cba7c7fe7a6c4de3 · report fixture: signature boxes:Tensor/2/float, anchors:Tensor/2/float, encode_angle_to_vector:bool/0/bool, smooth_dim:bool/0/bool, norm_velo:bool/0/bool · returned Tensor · level recorded 2026-09-24
torch_to_np_dtype det3d/core/bbox/box_torch_ops.py ran Apache-2.0 (permissive) · 4dcdb0a71119c780 · report fixture: signature ttype:dtype/0/? · returned Float32DType · level recorded 2026-09-24
unmap in 5 papers det3d/core/anchor/target_ops.py ran Apache-2.0 (permissive) · 2902bedb7c18b1a1 · report fixture: signature data:ndarray/1/int, count:int/0/int, inds:ndarray/1/int, fill:int/0/int · returned ndarray · level recorded 2026-09-25
parse in 85 papers det3d/visualization/netviz.py unverified Apache-2.0 (permissive) · 50ded6a49b80467e · report

Tasks

3D Object DetectionAutonomous DrivingObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection nuScenes MEGVII NDS 0.63.3 #372 of 372 Archive leaderboard report
3D Object Detection nuScenes MEGVII mAP 0.528 #372 of 372 Archive leaderboard report
3D Object Detection nuScenes LiDAR only CBGS NDS 63.3 #6 of 7 Archive leaderboard report
3D Object Detection nuScenes LiDAR only CBGS NDS (val) 62.3 #6 of 7 Archive leaderboard report
3D Object Detection nuScenes LiDAR only CBGS mAP 52.8 #6 of 7 Archive leaderboard report
3D Object Detection nuScenes LiDAR only CBGS mAP (val) 50.6 #6 of 7 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.

Methods

3D ConvolutionConvolution

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