Papers › Frustum PointNets for 3D Object Detection from RGB-D Data

Frustum PointNets for 3D Object Detection from RGB-D Data

22 Nov 2017CVPR 2018 6arXiv:1711.08488archive 2025-07-28

Charles R. Qi, Wei Liu, Chenxia Wu, Hao Su, Leonidas J. Guibas

In this work, we study 3D object detection from RGB-D data in both indoor and outdoor scenes. While previous methods focus on images or 3D voxels, often obscuring natural 3D patterns and invariances of 3D data, we directly operate on raw point clouds by popping up RGB-D scans. However, a key challenge of this approach is how to efficiently localize objects in point clouds of large-scale scenes (region proposal). Instead of solely relying on 3D proposals, our method leverages both mature 2D object detectors and advanced 3D deep learning for object localization, achieving efficiency as well as high recall for even small objects. Benefited from learning directly in raw point clouds, our method is also able to precisely estimate 3D bounding boxes even under strong occlusion or with very sparse points. Evaluated on KITTI and SUN RGB-D 3D detection benchmarks, our method outperforms the state of the art by remarkable margins while having real-time capability.

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

The archive's official repository (charlesq34/frustum-pointnets) was not harvested; the 4 samples below come from 2 community repositories.

Syntology 4 code samples harvested from 2 repositories linked to this paper: 2 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; 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. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: community (archive-listed): 4 samples from 2 repositories, 2 ran (0 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 10 of its repositories that Syntology harvested for other papers:

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

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

charlesq34/frustum-pointnets officialmentioned on GitHubtfSyntology: not harvested report
BPMJG/annotated-F-pointnet mentioned on GitHubtfSyntology: not harvested report
BPMJG/annotated_pointnet mentioned on GitHubtfSyntology: not harvested report
CarloSgaravatti/HybridLateCascadeFusion mentioned on GitHubpytorchSyntology: not harvested report
FlowWind1999/pointnet-2 mentioned on GitHubtfSyntology: not harvested report
Harut0726/my-pointnet-tensorflow mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation (arXiv:1612.00593; that paper's own run record: 103 ran (of which 45 constructed an object rather than computing a result; 74 with no instrument failure: 0 honoured, 0 violated, 74 with no contract checked; 29 where Syntology's instrument failed) · 61 unverified); nothing checks that they implement this paper's method. report
Heedeok/frustum-pointnets-rgbd mentioned on GitHubtfSyntology: not harvested report
KaidongLi/tf-3d-alpha mentioned on GitHubtfSyntology: not harvested report
KhusDM/PointNetTree mentioned on GitHubtfSyntology: not harvested report
KiranAkadas/My_Pointnet_v2 mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation (arXiv:1612.00593; that paper's own run record: 103 ran (of which 45 constructed an object rather than computing a result; 74 with no instrument failure: 0 honoured, 0 violated, 74 with no contract checked; 29 where Syntology's instrument failed) · 61 unverified); nothing checks that they implement this paper's method. report
KiritoGH/frustum-pointnets mentioned on GitHubtfSyntology: not harvested report
LONG-9621/Extract_Point_3D mentioned on GitHubtfSyntology: not harvested report
LONG-9621/PointNet mentioned on GitHubtfSyntology: not harvested report
LONG-9621/PointNet- mentioned on GitHubtfSyntology: not harvested report
LebronGG/PointNet mentioned on GitHubtfSyntology: not harvested report
LinZhuoChen/pointnet2_multi_gpu mentioned on GitHubtfSyntology: not harvested report
Lw510107/PointNet mentioned on GitHubtfSyntology: not harvested report
Lw510107/pointnet-2018.6.27- mentioned on GitHubtfSyntology: not harvested report
MikeS96/3d_obj_detection mentioned on GitHubSyntology: not harvested report
ModelBunker/PointNet-TensorFlow mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation (arXiv:1612.00593; that paper's own run record: 103 ran (of which 45 constructed an object rather than computing a result; 74 with no instrument failure: 0 honoured, 0 violated, 74 with no contract checked; 29 where Syntology's instrument failed) · 61 unverified); nothing checks that they implement this paper's method. report
RPFey/frustum-pointnets mentioned on GitHubtfSyntology: not harvested report
SEU-SRTP-GROUP/frustum-pointnet-original mentioned on GitHubtfSyntology: not harvested report
Smiler-Jin/frustum_pointnet mentioned on GitHubtfSyntology: not harvested report
VaanHUANG/CSCI5210HW1 mentioned on GitHubtfSyntology: not harvested report
Veincore/f-pointnet mentioned on GitHubSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
Yang2446/pointnet mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PCPNET: Learning Local Shape Properties from Raw Point Clouds (arXiv:1710.04954; 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
Yc174/frustum-pointnets mentioned on GitHubtfSyntology: not harvested report
YiruS/pointnet_adversarial mentioned on GitHubtfSyntology: not harvested report
ZhihaoZhu/PointNet-Implementation-Tensorflow mentioned on GitHubtfSyntology: not harvested report
abdullahozer11/Segmentation-and-Classification-of-Objects-in-Point-Clouds mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation (arXiv:1612.00593; that paper's own run record: 103 ran (of which 45 constructed an object rather than computing a result; 74 with no instrument failure: 0 honoured, 0 violated, 74 with no contract checked; 29 where Syntology's instrument failed) · 61 unverified); nothing checks that they implement this paper's method. report
ahmed-anas/thesis-pointnet mentioned on GitHubtfSyntology: not harvested report
alpemek/ais3d mentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 unverified report
arbaza/3D-object-detection-KITTI mentioned on GitHubpytorchSyntology: not harvested report
aviros/pointnet_totations mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation (arXiv:1612.00593; that paper's own run record: 103 ran (of which 45 constructed an object rather than computing a result; 74 with no instrument failure: 0 honoured, 0 violated, 74 with no contract checked; 29 where Syntology's instrument failed) · 61 unverified); nothing checks that they implement this paper's method. report
aviros/roatationPointnet mentioned on GitHubtfSyntology: not harvested report
ben0110/Frustum_pointnet_2D mentioned on GitHubtfSyntology: not harvested report
ben0110/Radar-Pointnet-PARA mentioned on GitHubtfSyntology: not harvested report
ben0110/frustum-pointnets_RSC_RADAR_fil_PC_batch_para mentioned on GitHubtfSyntology: not harvested report
brbzjl/pointnet2 mentioned on GitHubtfSyntology: not harvested report
bt77/pointnet mentioned on GitHubtfSyntology: not harvested report
charlesq34/pointnet mentioned on GitHubtfSyntology: not harvested report
charlesq34/pointnet2 mentioned on GitHubtfSyntology: not harvested report
chonepieceyb/reading-frustum-pointnets-code mentioned on GitHubtfSyntology: not harvested report
coconutzs/PointNet_zs mentioned on GitHubtfSyntology: not harvested report
dwtstore/sfm1 mentioned on GitHubtfSyntology: not harvested report
houseleo/pointnet mentioned on GitHubtfSyntology: not harvested report
jediofgever/PointNet_Custom_Object_Detection mentioned on GitHubtfSyntology: not harvested report
kargarisaac/3d-MNIST-classification-PointNet mentioned on GitHubtfSyntology: not harvested report
kargarisaac/PointNet-SemSeg-VKITTI3D mentioned on GitHubtfSyntology: not harvested report
lingzhang1/pointnet_tensorflow mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation (arXiv:1612.00593; that paper's own run record: 103 ran (of which 45 constructed an object rather than computing a result; 74 with no instrument failure: 0 honoured, 0 violated, 74 with no contract checked; 29 where Syntology's instrument failed) · 61 unverified); nothing checks that they implement this paper's method. report
llzlcl/pointcloud-segment mentioned on GitHubtfSyntology: not harvested report
tancik/fpointnets_image_features mentioned on GitHubtfSyntology: not harvested report
tonysy/pointnet2_tf mentioned on GitHubtfSyntology: not harvested report
voidrank/Geo-CNN mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN (arXiv:1811.07782; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
wonderland-dsg/pointnet-grid mentioned on GitHubtfSyntology: not harvested report
wuryantoAji/POINTNET mentioned on GitHubtfSyntology: not harvested report
xurui1217/pointnet2-master mentioned on GitHubtfSyntology: not harvested report
y2kmz/pointnetv2 mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation (arXiv:1612.00593; that paper's own run record: 103 ran (of which 45 constructed an object rather than computing a result; 74 with no instrument failure: 0 honoured, 0 violated, 74 with no contract checked; 29 where Syntology's instrument failed) · 61 unverified); nothing checks that they implement this paper's method. report
yanx27/Pointnet mentioned on GitHubtfSyntology: not harvested report
ytng001/sensemaking mentioned on GitHubtfSyntology: not harvested report
zenroad/modifypointnet mentioned on GitHubtfSyntology: not harvested report
zgx0534/pointnet_win mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation (arXiv:1612.00593; that paper's own run record: 103 ran (of which 45 constructed an object rather than computing a result; 74 with no instrument failure: 0 honoured, 0 violated, 74 with no contract checked; 29 where Syntology's instrument failed) · 61 unverified); nothing checks that they implement this paper's method. report
2023-MindSpore-1/ms-code-214 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code9 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code10 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code7 mindsporeSyntology: not harvested report
code-implementation1/Code9 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

4 samples harvested: 2 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; 2 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure 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
2unverified

Licence: 2 of the 4 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 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.

Veincore/f-pointnet community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
get_lidar_in_image_fov in 5 papers infer/prep_data_infer.py ran · our draft was wrong Apache-2.0 (permissive) · 47397a2377a470c7 · report fixture: signature pc_velo:ndarray/2/float, calib:MockCalib/0/?, xmin:int/0/int, ymin:int/0/int, xmax:int/0/int, ymax:int/0/int, return_more:bool/0/bool, clip_distance:float/0/float · returned ndarray · level recorded 2026-09-22
transform_bbox_inverse infer/prep_data_infer.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 6a56057817a2ab9b · report fixture: signature bbox_lists:ndarray/2/float, img_ori_shape:tuple/1/int, img_shape:tuple/1/int · returned ndarray · level recorded 2026-09-22
alpemek/ais3d community (archive-listed) 2 samples, 0 ran · 2 unverified
computeBox3D computeBox3D.py unverified no licence file found · pointer only · f95b1b0c4fc91241 · report
projectToImage computeBox3D.py unverified no licence file found · pointer only · 0b905dfd500cd40d · report

Tasks

3D Object DetectionObjectObject DetectionObject Detection In Indoor ScenesObject LocalizationRegion Proposal

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection KITTI Cars Easy Frustum PointNets AP 81.2% #22 of 26 Archive leaderboard report
3D Object Detection KITTI Cars Easy val F-PointNet [Qi:2018fd] AP 83.26 #8 of 11 Archive leaderboard report
3D Object Detection KITTI Cars Hard Frustum PointNets AP 62.19% #22 of 25 Archive leaderboard report
3D Object Detection KITTI Cars Hard val F-PointNet [Qi:2018fd] AP 62.56 #8 of 10 Archive leaderboard report
3D Object Detection KITTI Cars Moderate val F-PointNet [Qi:2018fd] AP 69.28 #9 of 11 Archive leaderboard report
3D Object Detection KITTI Cyclist Easy val F-PointNet++ [Qi:2018fd] AP 77.15 #3 of 4 Archive leaderboard report
3D Object Detection KITTI Cyclist Easy val F-PointNet [Qi:2018fd] AP 74.54 #4 of 4 Archive leaderboard report
3D Object Detection KITTI Cyclist Hard val F-PointNet++ [Qi:2018fd] AP 53.37 #3 of 4 Archive leaderboard report
3D Object Detection KITTI Cyclist Hard val F-PointNet [Qi:2018fd] AP 52.65 #4 of 4 Archive leaderboard report
3D Object Detection KITTI Cyclist Moderate val F-PointNet++ [Qi:2018fd] AP 56.49 #3 of 4 Archive leaderboard report
3D Object Detection KITTI Cyclist Moderate val F-PointNet [Qi:2018fd] AP 55.95 #4 of 4 Archive leaderboard report
3D Object Detection KITTI Cyclists Easy Frustum PointNets AP 71.96% #9 of 12 Archive leaderboard report
3D Object Detection KITTI Cyclists Hard Frustum PointNets AP 50.39% #9 of 12 Archive leaderboard report
3D Object Detection KITTI Cyclists Moderate Frustum PointNets AP 56.77% #10 of 13 Archive leaderboard report
3D Object Detection KITTI Pedestrian Easy val F-PointNet++ [Qi:2018fd] AP 70.00 #2 of 4 Archive leaderboard report
3D Object Detection KITTI Pedestrian Easy val F-PointNet [Qi:2018fd] AP 65.08 #4 of 4 Archive leaderboard report
3D Object Detection KITTI Pedestrian Hard val F-PointNet++ [Qi:2018fd] AP 53.59 #3 of 4 Archive leaderboard report
3D Object Detection KITTI Pedestrian Hard val F-PointNet [Qi:2018fd] AP 49.28 #4 of 4 Archive leaderboard report
3D Object Detection KITTI Pedestrian Moderate val F-PointNet++ [Qi:2018fd] AP 61.32 #2 of 4 Archive leaderboard report
3D Object Detection KITTI Pedestrian Moderate val F-PointNet [Qi:2018fd] AP 55.85 #4 of 4 Archive leaderboard report
3D Object Detection KITTI Pedestrians Easy Frustum PointNets AP 51.21% #6 of 9 Archive leaderboard report
3D Object Detection KITTI Pedestrians Hard Frustum PointNets AP 40.23% #6 of 9 Archive leaderboard report
3D Object Detection KITTI Pedestrians Moderate Frustum PointNets AP 42.15% #9 of 12 Archive leaderboard report
3D Object Detection SUN-RGBD Frustum PointNets mAP@0.25 54.0 #7 of 8 Archive leaderboard report
3D Object Detection SUN-RGBD val F-PointNet Inference Speed (s) 0.12 #25 of 32 Archive leaderboard report
3D Object Detection SUN-RGBD val F-PointNet mAP@0.25 54.0 #25 of 32 Archive leaderboard report
Birds Eye View Object Detection KITTI Cyclists Moderate F-PointNet AP 61.96% #4 of 6 Archive leaderboard report
Birds Eye View Object Detection KITTI Pedestrians Moderate F-PointNet AP 50.22% #5 of 6 Archive leaderboard report
Object Detection KITTI Cars Hard F-PointNet AP 62.19 #4 of 5 Archive leaderboard report
Object Detection In Indoor Scenes SUN RGB-D Frustum Pointnet (RGB) AP 0.5 56.8 #2 of 7 Archive leaderboard report
Object Localization KITTI Cars Easy Frustum PointNets AP 88.7% #2 of 2 Archive leaderboard report
Object Localization KITTI Cars Hard Frustum PointNets AP 75.33% #2 of 2 Archive leaderboard report
Object Localization KITTI Cars Moderate Frustum PointNets AP 84.0% #1 of 2 Archive leaderboard report
Object Localization KITTI Cyclists Easy Frustum PointNets AP 75.38% #1 of 2 Archive leaderboard report
Object Localization KITTI Cyclists Hard Frustum PointNets AP 54.68% #1 of 2 Archive leaderboard report
Object Localization KITTI Cyclists Moderate Frustum PointNets AP 61.96% #1 of 2 Archive leaderboard report
Object Localization KITTI Pedestrians Easy Frustum PointNets AP 58.09% #1 of 2 Archive leaderboard report
Object Localization KITTI Pedestrians Hard Frustum PointNets AP 47.2% #2 of 3 Archive leaderboard report
Object Localization KITTI Pedestrians Moderate Frustum PointNets AP 50.22% #2 of 3 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