Papers › Mask3D: Mask Transformer for 3D Semantic Instance Segmentation

Mask3D: Mask Transformer for 3D Semantic Instance Segmentation

6 Oct 2022arXiv:2210.03105archive 2025-07-28

Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe

Modern 3D semantic instance segmentation approaches predominantly rely on specialized voting mechanisms followed by carefully designed geometric clustering techniques. Building on the successes of recent Transformer-based methods for object detection and image segmentation, we propose the first Transformer-based approach for 3D semantic instance segmentation. We show that we can leverage generic Transformer building blocks to directly predict instance masks from 3D point clouds. In our model called Mask3D each object instance is represented as an instance query. Using Transformer decoders, the instance queries are learned by iteratively attending to point cloud features at multiple scales. Combined with point features, the instance queries directly yield all instance masks in parallel. Mask3D has several advantages over current state-of-the-art approaches, since it neither relies on (1) voting schemes which require hand-selected geometric properties (such as centers) nor (2) geometric grouping mechanisms requiring manually-tuned hyper-parameters (e.g. radii) and (3) enables a loss that directly optimizes instance masks. Mask3D sets a new state-of-the-art on ScanNet test (+6.2 mAP), S3DIS 6-fold (+10.1 mAP), STPLS3D (+11.2 mAP) and ScanNet200 test (+12.4 mAP).

PaperPDFCodeCode 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="2210.03105")

Code

Syntology Ran 2 of 10 code samples harvested from 1 repository linked to this paper; 8 have no recorded run. Of those that ran: 1 ran · fixture could not drive it; 1 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 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.

jonasschult/mask3d officialmentioned in papermentioned on GitHubpytorchMIT 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; 0 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 · fixture could not drive it
1ran
8unverified

Licence: 0 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 jonasschult/mask3d. “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.

make_pred_info jonasschult/mask3d/benchmark/evaluate_semantic_instance.py official repository ran MIT (permissive) · da426b749d2b3e6b · report
shift_scale_points jonasschult/mask3d/models/position_embedding.py official repository ran · fixture could not drive it MIT (permissive) · 818099bdffc93897 · report
batch_dice_loss jonasschult/mask3d/models/matcher.py official repository unverified MIT (permissive) · bc2cb481a75c370d · report
batch_sigmoid_ce_loss jonasschult/mask3d/models/matcher.py official repository unverified MIT (permissive) · 1edd24985036b0bf · report
calculate_uncertainty jonasschult/mask3d/models/criterion.py official repository unverified MIT (permissive) · 2dcb8123d89bb1ff · report
compute_averages jonasschult/mask3d/benchmark/evaluate_semantic_instance.py official repository unverified MIT (permissive) · fee7d4228b4a171d · report
dice_loss jonasschult/mask3d/models/criterion.py official repository unverified MIT (permissive) · 89f75e54ff128be0 · report
evaluate_matches jonasschult/mask3d/benchmark/evaluate_semantic_instance.py official repository unverified MIT (permissive) · 6f0bdc00532cb7e6 · report
nested_tensor_from_tensor_list jonasschult/mask3d/models/misc.py official repository unverified MIT (permissive) · 58cc9ff3bf75e753 · report
sigmoid_ce_loss jonasschult/mask3d/models/criterion.py official repository unverified MIT (permissive) · d0c61e8dba511aa3 · report

Tasks

3D Instance Segmentation3D Semantic Instance SegmentationInstance SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Instance Segmentation S3DIS Mask3D AP@50 75.5 #2 of 21 Archive leaderboard report
3D Instance Segmentation S3DIS Mask3D mAP 64.5 #2 of 21 Archive leaderboard report
3D Instance Segmentation STPLS3D Mask3D AP 57.3 #2 of 9 Archive leaderboard report
3D Instance Segmentation STPLS3D Mask3D AP25 81.6 #2 of 9 Archive leaderboard report
3D Instance Segmentation STPLS3D Mask3D AP50 74.3 #2 of 9 Archive leaderboard report
3D Instance Segmentation ScanNet(v2) Mask3D mAP 55.2 #7 of 32 Archive leaderboard report
3D Instance Segmentation ScanNet(v2) Mask3D mAP @ 50 78.0 #7 of 32 Archive leaderboard report
3D Instance Segmentation ScanNet(v2) Mask3D mAP@25 87.0 #7 of 32 Archive leaderboard report
3D Instance Segmentation ScanNet200 Mask3D mAP 27.8 #2 of 5 Archive leaderboard report
Semantic Segmentation Replica Mask3D mIoU 22.6 #3 of 5 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTestTransformer

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