Papers › PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

31 Dec 2019CVPR 2020 6arXiv:1912.13192archive 2025-07-28

Shaoshuai Shi, Chaoxu Guo, Li Jiang, Zhe Wang, Jianping Shi, Xiaogang Wang, Hongsheng Li

We present a novel and high-performance 3D object detection framework, named PointVoxel-RCNN (PV-RCNN), for accurate 3D object detection from point clouds. Our proposed method deeply integrates both 3D voxel Convolutional Neural Network (CNN) and PointNet-based set abstraction to learn more discriminative point cloud features. It takes advantages of efficient learning and high-quality proposals of the 3D voxel CNN and the flexible receptive fields of the PointNet-based networks. Specifically, the proposed framework summarizes the 3D scene with a 3D voxel CNN into a small set of keypoints via a novel voxel set abstraction module to save follow-up computations and also to encode representative scene features. Given the high-quality 3D proposals generated by the voxel CNN, the RoI-grid pooling is proposed to abstract proposal-specific features from the keypoints to the RoI-grid points via keypoint set abstraction with multiple receptive fields. Compared with conventional pooling operations, the RoI-grid feature points encode much richer context information for accurately estimating object confidences and locations. Extensive experiments on both the KITTI dataset and the Waymo Open dataset show that our proposed PV-RCNN surpasses state-of-the-art 3D detection methods with remarkable margins by using only point clouds. Code is available at https://github.com/open-mmlab/OpenPCDet.

PaperPDFConference PDFCodeCode 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/OpenPCDet) is linked to this paper; the 16 samples below come from 3 community repositories. Syntology harvested code from open-mmlab/OpenPCDet for another paper.

open-mmlab/OpenPCDet: Syntology's graph links these samples to arXiv:2503.08639 (its page on Syntology; that paper's own run record: 7 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method.

Syntology 16 code samples harvested from 3 repositories linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 16 samples from 3 repositories, 13 ran (12 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.

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.

open-mmlab/OpenPCDet officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to arXiv:2503.08639 (its page on Syntology; that paper's own run record: 7 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
KPeng9510/MASS mentioned on GitHubpytorchApache-2.0Syntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
KangchengLiu/FAC_Foreground_Aware_Contrast mentioned on GitHubpytorchSyntology: not harvested report
KangchengLiu/RM3D mentioned on GitHubpytorchSyntology: not harvested report
jhultman/PV-RCNN mentioned on GitHubpytorchMITSyntology: 7 samples, 6 ran (0 instrument-failed) · 1 unverified report
sshaoshuai/PV-RCNN mentioned on GitHubpytorchSyntology: not harvested report
sunshenggu/xc_eval_pcdet mentioned on GitHubpytorchApache-2.0Syntology: 5 samples, 4 ran (1 instrument-failed) · 1 unverified report
2023-MindSpore-1/ms-code-220 mindsporeSyntology: not harvested report
2023-MindSpore-1/ms-code-6 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code6 mindsporeSyntology: not harvested report
code-implementation1/Code5 mindsporeSyntology: not harvested report
code-implementation1/Code7 mindsporeSyntology: 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

16 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 3 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
12ran
3unverified

Licence: 3 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 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 3 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.

KPeng9510/MASS community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
cfg_from_yaml_file in 59 papers pcdet/config.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 696fe155f9990d38 · report fixture: signature cfg_file:str/0/str, config:dict/0/? · returned EasyDict · level recorded 2026-09-25
merge_new_config in 59 papers pcdet/config.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 392c0cf3a1b07b12 · report fixture: signature config:dict/0/?, new_config:dict/0/? · returned EasyDict · level recorded 2026-09-25
recursive_glob in 12 papers label_processing_tools/gt_img.py ran fingerprinted Apache-2.0 (permissive) · 513d282e7c3d723b · report fixture: signature rootdir:str/0/str, suffix:str/0/str · returned list · level recorded 2026-09-24
get_corner_loss_lidar in 51 papers pcdet/utils/loss_utils.py unverified Apache-2.0 (permissive) · 1780d388cc532a6d · report
jhultman/PV-RCNN community (archive-listed) 7 samples, 6 ran (0 instrument-failed) · 1 unverified
box3d_to_bev_corners vision3d/core/geometry.py ran MIT (permissive) · 174d1179819a5285 · report fixture: signature boxes:ndarray/2/float · returned ndarray · level recorded 2026-09-24
clipped_percentile vision3d/core/bev_drawer.py ran fingerprinted MIT (permissive) · 52b41e094461dcb7 · report fixture: signature x:ndarray/1/float, p:int/0/int · returned ndarray · level recorded 2026-09-24
decode in 57 papers vision3d/core/box_encode.py ran MIT (permissive) · ac13c2ae56957af1 · report fixture: signature deltas:Tensor/2/float, anchors:Tensor/2/float · returned Tensor · level recorded 2026-09-24
encode in 73 papers vision3d/core/box_encode.py ran MIT (permissive) · 744899d028ceaeb6 · report fixture: signature boxes:Tensor/2/float, anchors:Tensor/2/float · returned Tensor · level recorded 2026-09-24
points_in_convex_polygon vision3d/core/geometry.py ran MIT (permissive) · 808098fcbc06df78 · report fixture: signature points:ndarray/2/float, polygon:ndarray/3/float, ccw:bool/0/bool · returned ndarray · level recorded 2026-09-24
torchify_anchor_attributes vision3d/core/anchor_generator.py ran MIT (permissive) · bdb22c3ca2ff101f · report fixture: signature cfg:Config/0/? · returned dict · level recorded 2026-09-24
make_bev_map vision3d/core/bev_drawer.py unverified MIT (permissive) · 7641b2131879260e · report
sunshenggu/xc_eval_pcdet community (archive-listed) 5 samples, 4 ran (1 instrument-failed) · 1 unverified
div_up in 10 papers pcdet/datasets/kitti/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 pcdet/datasets/kitti/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 pcdet/datasets/kitti/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
limit_period pcdet/datasets/waymo/waymo_eval.py ran fingerprinted Apache-2.0 (permissive) · 5d754caea58766b7 · report fixture: signature val:ndarray/1/float, offset:float/0/float, period:float/0/float · returned ndarray · level recorded 2026-09-24
get_kitti_info_path in 7 papers pcdet/datasets/kitti/kitti_object_eval_python/kitti_common.py unverified Apache-2.0 (permissive) · f027b5ae160547ce · report

Tasks

3D Object DetectionObjectObject DetectionRobust 3D Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection KITTI Cars Easy PV-RCNN AP 90.25% #8 of 26 Archive leaderboard report
3D Object Detection KITTI Cars Hard PV-RCNN AP 76.82% #8 of 25 Archive leaderboard report
3D Object Detection KITTI Cyclists Easy PV-RCNN AP 78.60% #6 of 12 Archive leaderboard report
3D Object Detection KITTI Cyclists Hard PV-RCNN AP 57.65% #3 of 12 Archive leaderboard report
3D Object Detection KITTI Cyclists Moderate PV-RCNN AP 63.71% #5 of 13 Archive leaderboard report
3D Object Detection waymo all_ns PV-RCNN APH/L2 71.52 #2 of 2 Archive leaderboard report
3D Object Detection waymo cyclist PV-RCNN APH/L2 71.16 #5 of 7 Archive leaderboard report
3D Object Detection waymo pedestrian PV-RCNN APH/L2 70.16 #6 of 7 Archive leaderboard report
3D Object Detection waymo vehicle PV-RCNN APH/L2 73.23 #4 of 8 Archive leaderboard report
Birds Eye View Object Detection KITTI Cars Easy PV-RCNN AP 94.98 #2 of 9 Archive leaderboard report
Birds Eye View Object Detection KITTI Cars Hard PV-RCNN AP 86.14 #3 of 8 Archive leaderboard report
Birds Eye View Object Detection KITTI Cars Moderate PV-RCNN AP 90.65% #2 of 9 Archive leaderboard report
Birds Eye View Object Detection KITTI Cyclists Easy PV-RCNN AP 82.49 #1 of 2 Archive leaderboard report
Birds Eye View Object Detection KITTI Cyclists Hard PV-RCNN AP 62.41 #1 of 2 Archive leaderboard report
Birds Eye View Object Detection KITTI Cyclists Moderate PV-RCNN AP 68.89% #1 of 6 Archive leaderboard report
Robust 3D Object Detection KITTI-C PV-RCNN mean Corruption Error (mCE) 90.04% #1 of 5 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