Papers › 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks

4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks

18 Apr 2019CVPR 2019 6arXiv:1904.08755archive 2025-07-28

Christopher Choy, JunYoung Gwak, Silvio Savarese

In many robotics and VR/AR applications, 3D-videos are readily-available sources of input (a continuous sequence of depth images, or LIDAR scans). However, those 3D-videos are processed frame-by-frame either through 2D convnets or 3D perception algorithms. In this work, we propose 4-dimensional convolutional neural networks for spatio-temporal perception that can directly process such 3D-videos using high-dimensional convolutions. For this, we adopt sparse tensors and propose the generalized sparse convolution that encompasses all discrete convolutions. To implement the generalized sparse convolution, we create an open-source auto-differentiation library for sparse tensors that provides extensive functions for high-dimensional convolutional neural networks. We create 4D spatio-temporal convolutional neural networks using the library and validate them on various 3D semantic segmentation benchmarks and proposed 4D datasets for 3D-video perception. To overcome challenges in the 4D space, we propose the hybrid kernel, a special case of the generalized sparse convolution, and the trilateral-stationary conditional random field that enforces spatio-temporal consistency in the 7D space-time-chroma space. Experimentally, we show that convolutional neural networks with only generalized 3D sparse convolutions can outperform 2D or 2D-3D hybrid methods by a large margin. Also, we show that on 3D-videos, 4D spatio-temporal convolutional neural networks are robust to noise, outperform 3D convolutional neural networks and are faster than the 3D counterpart in some cases.

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 (StanfordVL/MinkowskiEngine) was not harvested; the 2 samples below come from 1 community repository.

Syntology 2 code samples harvested from 1 repository linked to this paper: 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) · 1 unverified. Where Syntology's instrument failed: 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): 2 samples from 1 repository, 1 ran (0 with no instrument failure; 1 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

StanfordVL/MinkowskiEngine officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
NVIDIA/MinkowskiEngine mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
buildingnet/buildingnet_dataset mentioned on GitHubpytorchSyntology: not harvested report
dkoh0207/lartpc_minkowski mentioned on GitHubpytorchSyntology: not harvested report
ldkong1205/Robo3D mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FRNet: Frustum-Range Networks for Scalable LiDAR Segmentation (arXiv:2312.04484; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
mit-han-lab/spvnas mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution (arXiv:2007.16100; that paper's own run record: 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); nothing checks that they implement this paper's method. report
shwoo93/minkowskiengine mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested 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

2 samples harvested: 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) · 1 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; the contract check could not run
1unverified

Licence: 2 of the 2 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 NVIDIA/MinkowskiEngine. “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.

NVIDIA/MinkowskiEngine community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
normalize_color examples/indoor.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted licence not identified · pointer only · ba78a3f6ba016b4f · report fixture: signature color:Tensor/2/float, is_color_in_range_0_255:bool/0/bool · returned Tensor · level recorded 2026-09-22
load_file in 52 papers examples/indoor.py unverified licence not identified · pointer only · 460808fbce44a8d8 · report

Tasks

3D Semantic Segmentation4D Spatio Temporal Semantic SegmentationRobust 3D Semantic SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Semantic Segmentation STPLS3D MinkowskiNet mIOU 51.3 #3 of 6 Archive leaderboard report
3D Semantic Segmentation ScanNet++ SpUNet (MinkowskiNet) Top-1 IoU 0.456 #7 of 8 Archive leaderboard report
3D Semantic Segmentation ScanNet++ SpUNet (MinkowskiNet) Top-3 IoU 0.683 #7 of 8 Archive leaderboard report
3D Semantic Segmentation ScanNet200 MinkUNet test mIoU 25.3 #16 of 16 Archive leaderboard report
3D Semantic Segmentation ScanNet200 MinkUNet val mIoU 25.0 #16 of 16 Archive leaderboard report
3D Semantic Segmentation ScribbleKITTI MinkowskiNet mIoU 55.0 #4 of 6 Archive leaderboard report
3D Semantic Segmentation WildScenes MinkUNet mIoU 36.53 #3 of 4 Archive leaderboard report
3D Semantic Segmentation WildScenes MinkUNet mIoU (Env DA) 30.78 #3 of 4 Archive leaderboard report
3D Semantic Segmentation WildScenes MinkUNet mIoU (Temporal DA) 27.20 #3 of 4 Archive leaderboard report
Robust 3D Semantic Segmentation SemanticKITTI-C MinkUNet-18 mean Corruption Error (mCE) 100.00% #3 of 22 Archive leaderboard report
Robust 3D Semantic Segmentation SemanticKITTI-C MinkUNet-34 mean Corruption Error (mCE) 100.61% #5 of 22 Archive leaderboard report
Robust 3D Semantic Segmentation WOD-C MinkUNet-34 mean Corruption Error (mCE) 96.21% #1 of 5 Archive leaderboard report
Robust 3D Semantic Segmentation WOD-C MinkUNet-18 mean Corruption Error (mCE) 100.00% #3 of 5 Archive leaderboard report
Robust 3D Semantic Segmentation nuScenes-C MinkUNet-34 mean Corruption Error (mCE) 96.37% #2 of 12 Archive leaderboard report
Robust 3D Semantic Segmentation nuScenes-C MinkUNet-18 mean Corruption Error (mCE) 100.00% #5 of 12 Archive leaderboard report
Semantic Segmentation S3DIS MinkowskiNet Mean IoU 65.4 #37 of 54 Archive leaderboard report
Semantic Segmentation S3DIS MinkowskiNet Number of params 37.9M #37 of 54 Archive leaderboard report
Semantic Segmentation S3DIS MinkowskiNet Params (M) 37.9 #37 of 54 Archive leaderboard report
Semantic Segmentation S3DIS Area5 MinkowskiNet Number of params 37.9M #45 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 MinkowskiNet mAcc 71.7 #45 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 MinkowskiNet mIoU 65.4 #45 of 61 Archive leaderboard report
Semantic Segmentation ScanNet MinkowskiNet test mIoU 73.4 #27 of 45 Archive leaderboard report
Semantic Segmentation ScanNet MinkowskiNet val mIoU 72.2 #27 of 45 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

ConvolutionSparse ConvolutionsSubmanifold 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