Papers › Deep Hough Voting for 3D Object Detection in Point Clouds

Deep Hough Voting for 3D Object Detection in Point Clouds

21 Apr 2019ICCV 2019 10arXiv:1904.09664archive 2025-07-28

Charles R. Qi, Or Litany, Kaiming He, Leonidas J. Guibas

Current 3D object detection methods are heavily influenced by 2D detectors. In order to leverage architectures in 2D detectors, they often convert 3D point clouds to regular grids (i.e., to voxel grids or to bird's eye view images), or rely on detection in 2D images to propose 3D boxes. Few works have attempted to directly detect objects in point clouds. In this work, we return to first principles to construct a 3D detection pipeline for point cloud data and as generic as possible. However, due to the sparse nature of the data -- samples from 2D manifolds in 3D space -- we face a major challenge when directly predicting bounding box parameters from scene points: a 3D object centroid can be far from any surface point thus hard to regress accurately in one step. To address the challenge, we propose VoteNet, an end-to-end 3D object detection network based on a synergy of deep point set networks and Hough voting. Our model achieves state-of-the-art 3D detection on two large datasets of real 3D scans, ScanNet and SUN RGB-D with a simple design, compact model size and high efficiency. Remarkably, VoteNet outperforms previous methods by using purely geometric information without relying on color images.

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="1904.09664")

Code

Syntology Ran 2 of 10 code samples harvested from 3 repositories linked to this paper; 8 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong.

By repository: community (archive-listed): 10 samples from 3 repositories, 2 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.

facebookresearch/votenet officialmentioned in papermentioned on GitHubpytorch report
AsahiLiu/PointDetectron mentioned on GitHubpytorch report
Harut0726/votenet mentioned on GitHubpytorch report
LONG-9621/VoteNet mentioned on GitHubpytorchMIT report
NUAAXQ/MLCVNet mentioned on GitHubpytorchMIT report
hoangcuongbk80/VoteGrasp mentioned on GitHubpytorch report
ikh-innovation/roboweldar-votenet mentioned on GitHubpytorchMIT report
lanlan96/3drm mentioned on GitHubpytorch report
lanlan96/arm3d mentioned on GitHubpytorchMIT report
qq456cvb/VoteNet mentioned on GitHubtf report
zaiweizhang/H3DNet mentioned on GitHubpytorch report
cheng052/BRNet pytorchApache-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

10 samples harvested; 2 ran; 1 honoured the contract we drafted; 8 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 · honoured contract
1ran · our draft was wrong
8unverified

Licence: 10 of the 10 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.

batched_index_select lanlan96/arm3d/models/rn_module_ARM3D.py community (archive-listed) ran · our draft was wrong MIT recorded; this copy not marked cleared · pointer only · 582b2f1aa69315a0 · report
flip_axis_to_camera LONG-9621/VoteNet/models/ap_helper.py community (archive-listed) ran · honoured contract fingerprinted MIT recorded; this copy not marked cleared · pointer only · eddd23cbbb297813 · report
decode_scores LONG-9621/VoteNet/models/proposal_module.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 74b9f07a52401d24 · report
decode_scores_pred lanlan96/arm3d/models/proposal_module_with_rn.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · d3bb81c5e107b7f8 · report
flip_axis_to_depth LONG-9621/VoteNet/models/ap_helper.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · d638b0201b9a9ece · report
get_index lanlan96/arm3d/models/proposal_module_with_rn.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 4ff19e5ade7bd124 · report
preprocess_rbw_mesh ikh-innovation/roboweldar-votenet/inference_old.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 72259d174833ccb4 · report
set_bn_momentum_default LONG-9621/VoteNet/pointnet2/pytorch_utils.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 0ad12b1e8408e2f9 · report
softmax LONG-9621/VoteNet/models/ap_helper.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 1a034a72c15f9903 · report
switch_xy ikh-innovation/roboweldar-votenet/panelnet/panel_data.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 5db664d773dd81b5 · report

Tasks

3D Object Detection3D Object Detection From Monocular ImagesObjectObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection ARKitScenes VoteNet mAP@0.25 35.8 #4 of 4 Archive leaderboard report
3D Object Detection SUN-RGBD val VoteNet (Geo only) mAP@0.25 59.1 #22 of 32 Archive leaderboard report
3D Object Detection SUN-RGBD val VoteNet (Geo only) mAP@0.5 35.8 #22 of 32 Archive leaderboard report
3D Object Detection ScanNetV2 VoteNet mAP@0.25 58.6 #28 of 33 Archive leaderboard report
3D Object Detection ScanNetV2 VoteNet mAP@0.5 33.5 #28 of 33 Archive leaderboard report
3D Object Detection From Monocular Images KITTI-360 BoxNet AP25 23.59 #2 of 11 Archive leaderboard report
3D Object Detection From Monocular Images KITTI-360 BoxNet AP50 4.08 #2 of 11 Archive leaderboard report
3D Object Detection From Monocular Images KITTI-360 VoteNet AP25 30.61 #3 of 11 Archive leaderboard report
3D Object Detection From Monocular Images KITTI-360 VoteNet AP50 3.40 #3 of 11 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