Papers › Mix3D: Out-of-Context Data Augmentation for 3D Scenes

Mix3D: Out-of-Context Data Augmentation for 3D Scenes

5 Oct 2021arXiv:2110.02210archive 2025-07-28

Alexey Nekrasov, Jonas Schult, Or Litany, Bastian Leibe, Francis Engelmann

We present Mix3D, a data augmentation technique for segmenting large-scale 3D scenes. Since scene context helps reasoning about object semantics, current works focus on models with large capacity and receptive fields that can fully capture the global context of an input 3D scene. However, strong contextual priors can have detrimental implications like mistaking a pedestrian crossing the street for a car. In this work, we focus on the importance of balancing global scene context and local geometry, with the goal of generalizing beyond the contextual priors in the training set. In particular, we propose a "mixing" technique which creates new training samples by combining two augmented scenes. By doing so, object instances are implicitly placed into novel out-of-context environments and therefore making it harder for models to rely on scene context alone, and instead infer semantics from local structure as well. We perform detailed analysis to understand the importance of global context, local structures and the effect of mixing scenes. In experiments, we show that models trained with Mix3D profit from a significant performance boost on indoor (ScanNet, S3DIS) and outdoor datasets (SemanticKITTI). Mix3D can be trivially used with any existing method, e.g., trained with Mix3D, MinkowskiNet outperforms all prior state-of-the-art methods by a significant margin on the ScanNet test benchmark 78.1 mIoU. Code is available at: https://nekrasov.dev/mix3d/

PaperPDFCodeCode 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 (kumuji/mix3d) was not harvested; the 25 samples below come from 2 community repositories.

Syntology 25 code samples harvested from 2 repositories linked to this paper: 20 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 2 honoured, 0 violated, 16 with no contract checked; 2 where Syntology's instrument failed) · 5 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.

By repository: community (archive-listed): 25 samples from 2 repositories, 20 ran (18 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 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

kumuji/mix3d officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
TejasAnvekar/Mahalanobis-k-NN mentioned on GitHubpytorchMITSyntology: 15 samples, 12 ran (2 instrument-failed) · 3 unverified report
tejasanvekar/gpr-net mentioned on GitHubpytorchMITSyntology: 10 samples, 8 ran (0 instrument-failed) · 2 unverified 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

25 samples harvested: 20 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 2 honoured, 0 violated, 16 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
1ran · our draft was wrong
1ran; the contract check could not run
16ran
5unverified

Licence: 4 of the 25 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

TejasAnvekar/Mahalanobis-k-NN community (archive-listed) 15 samples, 12 ran (2 instrument-failed) · 3 unverified
DFMC DeepUME/UME.py ran fingerprinted MIT (permissive) · a2b3182bdc358857 · report fixture: signature pc:Tensor/3/float · returned Tensor · level recorded 2026-09-24
attention in 144 papers
census: 11 implementations from 10 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
DeepUME/model.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · 70ba9ecc422a6a48 · report fixture: signature query:Tensor/3/float, key:Tensor/3/float, value:Tensor/3/float, mask:Tensor/4/float, dropout:callable/0/? · returned tuple · level recorded 2026-09-22
clones in 92 papers DeepUME/model.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 6cdff690e29fd5e2 · report fixture: signature module:callable/0/?, N:int/0/int · returned ModuleList · level recorded 2026-09-22
hard_indicators DeepUME/UME.py ran MIT (permissive) · 0206bbb4587441ab · report fixture: signature point_features:Tensor/3/float, num_ws:int/0/int · returned Tensor · level recorded 2026-09-24
jitter_pointcloud in 7 papers dcp/data.py ran fingerprinted MIT (permissive) · 0eecf33500f60f91 · report fixture: signature pointcloud:ndarray/2/float, sigma:float/0/float, clip:float/0/float · returned ndarray · level recorded 2026-09-24
nearest_neighbor in 12 papers DeepUME/model.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · fd310351a155056f · report fixture: signature src:Tensor/2/float, dst:Tensor/2/float · returned tuple · level recorded 2026-09-22
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
DeepUME/data.py ran fingerprinted MIT (permissive) · 095bfc3f92857951 · report fixture: signature pc:ndarray/2/float · returned ndarray · level recorded 2026-09-24
pairwise_mahalanobis_distance dcp/model_mah.py ran fingerprinted MIT (permissive) · 92fd1a1a622c19d8 · report fixture: signature point_cloud_1:Tensor/3/float, point_cloud_2:Tensor/3/float · returned Tensor · level recorded 2026-09-24
quat2mat in 26 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
DeepUME/util.py ran fingerprinted MIT (permissive) · 838e2078ad9224da · report fixture: signature quat:Tensor/2/float · returned Tensor · level recorded 2026-09-24
reverse_transform_point_cloud DeepUME/util.py ran MIT (permissive) · 56fcfb1c378a6260 · report fixture: signature point_cloud:Tensor/3/float, rotation:Tensor/3/float, translation:Tensor/2/float · returned Tensor · level recorded 2026-09-24
translate_pointcloud in 15 papers dcp/data.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) here; the stored copy is pointer only · 791051c3e72b67d2 · report fixture: signature pointcloud:ndarray/2/float · returned ndarray · level recorded 2026-09-25
ume_matrix DeepUME/UME.py ran fingerprinted MIT (permissive) · 1e0a5e75cba2bea6 · report fixture: signature pc:Tensor/3/float, ws_activations:Tensor/3/float, num_ws:int/0/int · returned Tensor · level recorded 2026-09-24
load_data in 700 papers dcp/data.py unverified MIT (permissive) · 699001e108b5c983 · report
load_h5 in 10 papers DeepUME/data.py unverified MIT (permissive) · 704c600815a77cbe · report
transform_point_cloud in 6 papers DeepUME/util.py unverified MIT (permissive) · 501f02693edfd13f · report
tejasanvekar/gpr-net community (archive-listed) 10 samples, 8 ran (0 instrument-failed) · 2 unverified
Minkowski_distance networks/utils.py ran fingerprinted MIT (permissive) · 97dc68f521b0deb6 · report fixture: signature src:Tensor/3/float, dst:Tensor/3/float, p:int/0/int · returned Tensor · level recorded 2026-09-24
compute_confidence_interval in 6 papers utils.py ran fingerprinted MIT (permissive) · 03803e86ef774786 · report fixture: signature data:list/1/float · returned tuple · level recorded 2026-09-24
create_log_folders utils.py ran MIT (permissive) · d7188f94166c9631 · report fixture: signature args:Args/0/? · returned tuple · level recorded 2026-09-24
euclidean_dist in 69 papers
census: 12 implementations from 14 papers, 3 distinct outputs on one shared input
model/ProtoNet.py ran fingerprinted MIT (permissive) · fb8dd7b7cd7ed9dd · report fixture: signature x:Tensor/2/float, y:Tensor/2/float · returned Tensor · level recorded 2026-09-24
gather_idx networks/utils.py ran MIT (permissive) · dc112d101c6cd604 · report fixture: signature points:Tensor/3/float, idx:Tensor/2/int · returned Tensor · level recorded 2026-09-24
knn_idx networks/utils.py ran MIT (permissive) · cd1435192e01a1d7 · report fixture: signature xyz:Tensor/3/float, new_xyz:Tensor/3/float, K:int/0/int, p:int/0/int · returned tuple · level recorded 2026-09-24
make_data_for_FSL utils.py ran MIT (permissive) · 08036ac16900da17 · report fixture: signature train_x:ndarray/3/float, train_y:ndarray/1/int, test_x:ndarray/3/float, test_y:ndarray/1/int, total_cls:int/0/int, train_category:int/0/int, num_points:int/0/int, train_classes:NoneType/0/?, test_classes:NoneType/0/? · returned tuple · level recorded 2026-09-24
random_point_dropout in 5 papers dataloader.py ran fingerprinted MIT (permissive) · 05a0f3632a145154 · report fixture: signature pc:ndarray/3/float, max_dropout_ratio:float/0/float · returned ndarray · level recorded 2026-09-25
Poincare_dist model/ProtoNet.py unverified MIT (permissive) · 2706a5cfaf7acaca · report
load_data in 700 papers dataloader.py unverified MIT (permissive) · 08b8ba179d2bdf94 · report

Tasks

3D Semantic SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation ScanNet Mix3D test mIoU 78.1 #26 of 45 Archive leaderboard report
Semantic Segmentation ScanNet Mix3D val mIoU 73.6 #26 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

Test

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