Papers › Virtual Sparse Convolution for Multimodal 3D Object Detection

Virtual Sparse Convolution for Multimodal 3D Object Detection

4 Mar 2023CVPR 2023 1arXiv:2303.02314archive 2025-07-28

Hai Wu, Chenglu Wen, Shaoshuai Shi, Xin Li, Cheng Wang

Recently, virtual/pseudo-point-based 3D object detection that seamlessly fuses RGB images and LiDAR data by depth completion has gained great attention. However, virtual points generated from an image are very dense, introducing a huge amount of redundant computation during detection. Meanwhile, noises brought by inaccurate depth completion significantly degrade detection precision. This paper proposes a fast yet effective backbone, termed VirConvNet, based on a new operator VirConv (Virtual Sparse Convolution), for virtual-point-based 3D object detection. VirConv consists of two key designs: (1) StVD (Stochastic Voxel Discard) and (2) NRConv (Noise-Resistant Submanifold Convolution). StVD alleviates the computation problem by discarding large amounts of nearby redundant voxels. NRConv tackles the noise problem by encoding voxel features in both 2D image and 3D LiDAR space. By integrating VirConv, we first develop an efficient pipeline VirConv-L based on an early fusion design. Then, we build a high-precision pipeline VirConv-T based on a transformed refinement scheme. Finally, we develop a semi-supervised pipeline VirConv-S based on a pseudo-label framework. On the KITTI car 3D detection test leaderboard, our VirConv-L achieves 85% AP with a fast running speed of 56ms. Our VirConv-T and VirConv-S attains a high-precision of 86.3% and 87.2% AP, and currently rank 2nd and 1st, respectively. The code is available at https://github.com/hailanyi/VirConv.

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="2303.02314")

Code

Syntology Ran 3 of 9 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong; 1 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

hailanyi/virconv officialmentioned in papermentioned on GitHubpytorch 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

9 samples harvested; 3 ran; 1 honoured the contract we drafted; 6 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
1ran
6unverified

Licence: 0 of the 9 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 hailanyi/VirConv. “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.

X_TRANS hailanyi/VirConv/pcdet/models/backbones_3d/spconv_backbone.py official repository ran Apache-2.0 (permissive) · 641256c98796f0a5 · report
index2points hailanyi/VirConv/pcdet/models/backbones_3d/spconv_backbone.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · cfb5d7a9b7b762ff · report
replace_feature hailanyi/VirConv/pcdet/models/backbones_3d/spconv_backbone.py official repository ran · our draft was wrong Apache-2.0 (permissive) · fb89b701924ed8c6 · report
NRConvBlock hailanyi/VirConv/pcdet/models/backbones_3d/spconv_backbone.py official repository unverified Apache-2.0 (permissive) · 1bcb772a293d826d · report
VirConv8x hailanyi/VirConv/pcdet/models/backbones_3d/spconv_backbone.py official repository unverified Apache-2.0 (permissive) · 2817bb45ba222ef7 · report
index2uv hailanyi/VirConv/pcdet/models/backbones_3d/spconv_backbone.py official repository unverified Apache-2.0 (permissive) · 3f20dcdc51284524 · report
layer_voxel_discard hailanyi/VirConv/pcdet/models/backbones_3d/spconv_backbone.py official repository unverified Apache-2.0 (permissive) · c9bb9171cb692e4a · report
post_act_block hailanyi/VirConv/pcdet/models/backbones_3d/spconv_backbone.py official repository unverified Apache-2.0 (permissive) · c514e44067d93b93 · report
post_act_block2d hailanyi/VirConv/pcdet/models/backbones_3d/spconv_backbone.py official repository unverified Apache-2.0 (permissive) · fcb8815617b22031 · report

Tasks

3D Multi-Object Tracking3D Object DetectionDepth CompletionMultiple Object TrackingObjectObject DetectionPseudo Labelobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multiple Object Tracking KITTI Test (Online Methods) VirConvTrack HOTA 79.9 #7 of 34 Archive leaderboard report
Multiple Object Tracking KITTI Test (Online Methods) VirConvTrack IDSW 201 #7 of 34 Archive leaderboard report
Multiple Object Tracking KITTI Test (Online Methods) VirConvTrack MOTA 89.1 #7 of 34 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

SPEEDTest

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