Papers › Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution

Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution

31 Jul 2020ECCV 2020 8arXiv:2007.16100archive 2025-07-28

Haotian Tang, Zhijian Liu, Shengyu Zhao, Yujun Lin, Ji Lin, Hanrui Wang, Song Han

Self-driving cars need to understand 3D scenes efficiently and accurately in order to drive safely. Given the limited hardware resources, existing 3D perception models are not able to recognize small instances (e.g., pedestrians, cyclists) very well due to the low-resolution voxelization and aggressive downsampling. To this end, we propose Sparse Point-Voxel Convolution (SPVConv), a lightweight 3D module that equips the vanilla Sparse Convolution with the high-resolution point-based branch. With negligible overhead, this point-based branch is able to preserve the fine details even from large outdoor scenes. To explore the spectrum of efficient 3D models, we first define a flexible architecture design space based on SPVConv, and we then present 3D Neural Architecture Search (3D-NAS) to search the optimal network architecture over this diverse design space efficiently and effectively. Experimental results validate that the resulting SPVNAS model is fast and accurate: it outperforms the state-of-the-art MinkowskiNet by 3.3%, ranking 1st on the competitive SemanticKITTI leaderboard. It also achieves 8x computation reduction and 3x measured speedup over MinkowskiNet with higher accuracy. Finally, we transfer our method to 3D object detection, and it achieves consistent improvements over the one-stage detection baseline on KITTI.

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

Syntology 3 code samples harvested from 1 repository linked to this paper: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 3 samples from 1 repository, 2 ran (2 with no instrument failure; 0 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 4 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

mit-han-lab/spvnas officialmentioned on GitHubpytorchMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
chenfengxu714/image2point mentioned on GitHubpytorchBSD-2-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models (arXiv:2106.04180; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 2 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
mit-han-lab/torchsparse mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to TorchSparse: Efficient Point Cloud Inference Engine (arXiv:2204.10319; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
pjlab-adg/openpcseg mentioned on GitHubpytorchSyntology: not harvested report
pjlab-adg/pcseg mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase (arXiv:2309.05573; that paper's own run record: 6 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; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
Pointcept/Pointcept pytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Sonata: Self-Supervised Learning of Reliable Point Representations (arXiv:2503.16429; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 8 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

3 samples harvested: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 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.

2ran
1unverified

Licence: 0 of the 3 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 mit-han-lab/spvnas. “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.

mit-han-lab/spvnas official repository 3 samples, 2 ran (0 instrument-failed) · 1 unverified
create_label_map visualize.py ran fingerprinted MIT (permissive) · 0b71a9bb5beea7b9 · report fixture: signature num_classes:int/0/int · returned ndarray · level recorded 2026-09-25
make_divisible in 76 papers core/modules/dynamic_sparseop.py ran fingerprinted MIT (permissive) · 5353e04b2b5c5a26 · report fixture: signature x:int/0/int · returned int · level recorded 2026-09-25
download_url in 32 papers model_zoo.py unverified MIT (permissive) · 82545d97082ff5f4 · report

Tasks

3D Object Detection3D Semantic SegmentationLIDAR Semantic SegmentationNeural Architecture SearchObject DetectionRobust 3D Semantic SegmentationSelf-Driving Carsobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Semantic Segmentation SemanticKITTI SPVNAS test mIoU 66.4% #14 of 45 Archive leaderboard report
3D Semantic Segmentation SemanticKITTI SPVNAS val mIoU 64.7% #14 of 45 Archive leaderboard report
3D Semantic Segmentation WildScenes SPVCNN mIoU 36.78 #2 of 4 Archive leaderboard report
LIDAR Semantic Segmentation nuScenes SPVCNN++ test mIoU 0.811 #6 of 36 Archive leaderboard report
LIDAR Semantic Segmentation nuScenes SPVNAS test mIoU 0.77 #16 of 36 Archive leaderboard report
Robust 3D Semantic Segmentation SemanticKITTI-C SPVCNN-34 mean Corruption Error (mCE) 99.16% #1 of 22 Archive leaderboard report
Robust 3D Semantic Segmentation SemanticKITTI-C SPVCNN-18 mean Corruption Error (mCE) 100.30% #4 of 22 Archive leaderboard report
Robust 3D Semantic Segmentation WOD-C SPVCNN-34 mean Corruption Error (mCE) 98.72% #2 of 5 Archive leaderboard report
Robust 3D Semantic Segmentation WOD-C SPVCNN-18 mean Corruption Error (mCE) 103.60% #4 of 5 Archive leaderboard report
Robust 3D Semantic Segmentation nuScenes-C SPVCNN-34 mean Corruption Error (mCE) 97.45% #3 of 12 Archive leaderboard report
Robust 3D Semantic Segmentation nuScenes-C SPVCNN-18 mean Corruption Error (mCE) 106.65% #7 of 12 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

Convolution

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