Papers › PointPillars: Fast Encoders for Object Detection from Point Clouds

PointPillars: Fast Encoders for Object Detection from Point Clouds

14 Dec 2018CVPR 2019 6arXiv:1812.05784archive 2025-07-28

Alex H. Lang, Sourabh Vora, Holger Caesar, Lubing Zhou, Jiong Yang, Oscar Beijbom

Object detection in point clouds is an important aspect of many robotics applications such as autonomous driving. In this paper we consider the problem of encoding a point cloud into a format appropriate for a downstream detection pipeline. Recent literature suggests two types of encoders; fixed encoders tend to be fast but sacrifice accuracy, while encoders that are learned from data are more accurate, but slower. In this work we propose PointPillars, a novel encoder which utilizes PointNets to learn a representation of point clouds organized in vertical columns (pillars). While the encoded features can be used with any standard 2D convolutional detection architecture, we further propose a lean downstream network. Extensive experimentation shows that PointPillars outperforms previous encoders with respect to both speed and accuracy by a large margin. Despite only using lidar, our full detection pipeline significantly outperforms the state of the art, even among fusion methods, with respect to both the 3D and bird's eye view KITTI benchmarks. This detection performance is achieved while running at 62 Hz: a 2 - 4 fold runtime improvement. A faster version of our method matches the state of the art at 105 Hz. These benchmarks suggest that PointPillars is an appropriate encoding for object detection in point clouds.

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 (nutonomy/second.pytorch) is linked to this paper; the 15 samples below come from 5 community repositories. Syntology harvested code from nutonomy/second.pytorch for another paper.

nutonomy/second.pytorch: Syntology's graph links these samples to nuScenes: A multimodal dataset for autonomous driving (arXiv:1903.11027; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method.

Syntology 15 code samples harvested from 5 repositories linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 15 samples from 5 repositories, 13 ran (11 with no instrument failure; 2 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 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

nutonomy/second.pytorch officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to nuScenes: A multimodal dataset for autonomous driving (arXiv:1903.11027; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
LKLQQ/pointpillars mentioned on GitHubmindsporeApache-2.0Syntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
SmallMunich/nutonomy_pointpillars mentioned on GitHubpytorchMITSyntology: 8 samples, 6 ran (0 instrument-failed) · 2 unverified report
Uuuuuuho/Pillar_on_SoC mentioned on GitHubpytorchMITSyntology: not harvested report
hongru-seu/PointPilliar mentioned on GitHubmindsporeSyntology: not harvested report
hova88/Lidardet mentioned on GitHubpytorchSyntology: not harvested report
krullgit/realsense_3d_detection mentioned on GitHubtfSyntology: not harvested report
nvidia-ai-iot/lidar_ai_solution mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
sanjeewk/ppnet mentioned on GitHubSyntology: not harvested report
zhulf0804/pointpillars mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
gitee.com/gai-shaoyan/mind3d Syntology: not harvested report
2023-MindSpore-1/ms-code-215 mindsporeSyntology: not harvested report
MindSpore-paper-code-2/code2 mindsporeSyntology: not harvested report
PaddlePaddle/Paddle3D paddleApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to CAPE: Camera View Position Embedding for Multi-View 3D Object Detection (arXiv:2303.10209; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
airalcorn2/paved2paradise pytorchMITSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
hova88/PointPillars_MultiHead_40FPS pytorchGPL-3.0Syntology: not harvested report
isl-org/Open3D-ML pytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
open-mmlab/mmdetection3d pytorchApache-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

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

15 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 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 has not changed since , the first build that kept a record date for it; 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
1ran; the contract check could not run
11ran
2unverified

Licence: 1 of the 15 samples is 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 5 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.

LKLQQ/pointpillars community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
get_config in 203 papers src/utils.py ran Apache-2.0 (permissive) · 17815b44aafcf555 · report fixture: signature cfg_path:str/0/str · returned dict · level recorded 2026-09-26
get_dataset_keys src/builder/dataset_builder.py ran Apache-2.0 (permissive) · 4967576c687dfdf8 · report fixture: signature training:bool/0/bool, generate_bev:bool/0/bool · returned list · level recorded 2026-09-26
get_params_for_net src/utils.py ran Apache-2.0 (permissive) · 451d86db9edf4584 · report fixture: signature params:dict/0/? · returned dict · level recorded 2026-09-26
SmallMunich/nutonomy_pointpillars community (archive-listed) 8 samples, 6 ran (0 instrument-failed) · 2 unverified
is_line_segment_cross second/core/geometry.py ran MIT (permissive) · abc7a1803bf35228 · report fixture: signature lines1:ndarray/3/float, lines2:ndarray/3/float · returned ndarray · level recorded 2026-09-25
is_line_segment_intersection_jit second/core/geometry.py ran MIT (permissive) · de9bc527072ac4b0 · report fixture: signature lines1:ndarray/3/float, lines2:ndarray/3/float · returned ndarray · level recorded 2026-09-25
line_segment_intersection second/core/geometry.py ran MIT (permissive) · 6a7ad14559c54076 · report fixture: signature line1:ndarray/2/float, line2:ndarray/2/float, intersection:ndarray/1/float · returned bool · level recorded 2026-09-25
second_box_decode second/core/box_np_ops.py ran MIT (permissive) · 526cf943db7338d3 · report fixture: signature box_encodings:ndarray/2/float, anchors:ndarray/2/float, encode_angle_to_vector:bool/0/bool, smooth_dim:bool/0/bool · returned ndarray · level recorded 2026-09-25
second_box_encode in 5 papers second/core/box_np_ops.py ran MIT (permissive) · f2f3e2a705ddc55f · report fixture: signature boxes:ndarray/2/float, anchors:ndarray/2/float, encode_angle_to_vector:bool/0/bool, smooth_dim:bool/0/bool · returned ndarray · level recorded 2026-09-26
unmap in 5 papers second/core/target_ops.py ran MIT (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
create_target_np in 5 papers second/core/target_ops.py unverified MIT (permissive) · d2b64ea77c2d6d9f · report
riou_cc second/core/box_np_ops.py unverified MIT (permissive) · 2b3e25e607e98a0f · report
zhulf0804/pointpillars community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_score_thresholds evaluate.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed fingerprinted MIT (permissive) · a48052245131c33f · report fixture: signature tp_scores:list/1/float, total_num_valid_gt:int/0/int, num_sample_pts:int/0/int · returned list · level recorded 2026-09-22
airalcorn2/paved2paradise community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
create_depth_image paved2paradise.py ran MIT (permissive) · 566cdbac52dacce0 · report fixture: signature depths:ndarray/2/float, max_depth:float/0/float · returned Image · level recorded 2026-09-26
unlevel paved2paradise.py ran MIT (permissive) · c61b1e019a047572 · report fixture: signature moved_object_points:Tensor/2/float, bg_t:Tensor/1/float, bg_R:Tensor/2/float, moved_bbox:BBox/0/? · returned tuple · level recorded 2026-09-26
isl-org/Open3D-ML community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
unpack in 18 papers ml3d/tf/models/point_pillars.py ran · our draft was wrong licence not identified · pointer only · 1354276502be4aa8 · report fixture: signature flat_t:Tensor/1/float, counts:list/1/int · returned list · level recorded 2026-09-22

Tasks

3D Object DetectionAutonomous DrivingBirds Eye View Object DetectionObjectObject DetectionRobust 3D Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection DAIR-V2X-I PointPillars AP|R40(easy) 63.1 #6 of 9 Archive leaderboard report
3D Object Detection DAIR-V2X-I PointPillars AP|R40(hard) 54.0 #6 of 9 Archive leaderboard report
3D Object Detection DAIR-V2X-I PointPillars AP|R40(moderate) 54.0 #6 of 9 Archive leaderboard report
3D Object Detection KITTI Cars Easy PointPillars AP 79.05% #24 of 26 Archive leaderboard report
3D Object Detection KITTI Cyclists Easy PointPillars AP 75.78% #7 of 12 Archive leaderboard report
3D Object Detection KITTI Cyclists Hard PointPillars AP 52.92% #8 of 12 Archive leaderboard report
3D Object Detection KITTI Cyclists Moderate PointPillars AP 59.07% #8 of 13 Archive leaderboard report
3D Object Detection KITTI Pedestrians Moderate PointPillars AP 41.92% #10 of 12 Archive leaderboard report
3D Object Detection nuScenes LiDAR only PointPillar NDS 45.3 #7 of 7 Archive leaderboard report
3D Object Detection nuScenes LiDAR only PointPillar mAP 30.5 #7 of 7 Archive leaderboard report
Birds Eye View Object Detection KITTI Cars Easy PointPillars AP 88.35% #8 of 9 Archive leaderboard report
Birds Eye View Object Detection KITTI Cars Hard PointPillars AP 79.83 #5 of 8 Archive leaderboard report
Birds Eye View Object Detection KITTI Cars Moderate PointPillars AP 86.1% #6 of 9 Archive leaderboard report
Birds Eye View Object Detection KITTI Cyclists Moderate PointPillars AP 62.25% #3 of 6 Archive leaderboard report
Birds Eye View Object Detection KITTI Pedestrians Moderate PointPillars AP 50.23% #4 of 6 Archive leaderboard report
Robust 3D Object Detection KITTI-C SECOND mean Corruption Error (mCE) 95.93% #3 of 5 Archive leaderboard report
Robust 3D Object Detection KITTI-C PointPillars mean Corruption Error (mCE) 110.67% #5 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.

Methods

SPEED

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