Papers › Mask-Attention-Free Transformer for 3D Instance Segmentation

Mask-Attention-Free Transformer for 3D Instance Segmentation

4 Sep 2023ICCV 2023 1arXiv:2309.01692archive 2025-07-28

Xin Lai, Yuhui Yuan, Ruihang Chu, Yukang Chen, Han Hu, Jiaya Jia

Recently, transformer-based methods have dominated 3D instance segmentation, where mask attention is commonly involved. Specifically, object queries are guided by the initial instance masks in the first cross-attention, and then iteratively refine themselves in a similar manner. However, we observe that the mask-attention pipeline usually leads to slow convergence due to low-recall initial instance masks. Therefore, we abandon the mask attention design and resort to an auxiliary center regression task instead. Through center regression, we effectively overcome the low-recall issue and perform cross-attention by imposing positional prior. To reach this goal, we develop a series of position-aware designs. First, we learn a spatial distribution of 3D locations as the initial position queries. They spread over the 3D space densely, and thus can easily capture the objects in a scene with a high recall. Moreover, we present relative position encoding for the cross-attention and iterative refinement for more accurate position queries. Experiments show that our approach converges 4x faster than existing work, sets a new state of the art on ScanNetv2 3D instance segmentation benchmark, and also demonstrates superior performance across various datasets. Code and models are available at https://github.com/dvlab-research/Mask-Attention-Free-Transformer.

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="2309.01692")

Code

Syntology Ran 4 of 10 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 · fixture could not drive it; 2 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

dvlab-research/mask-attention-free-transformer 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

10 samples harvested; 4 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 · fixture could not drive it
2ran
6unverified

Licence: 10 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 dvlab-research/mask-attention-free-transformer. “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.

rle_decode dvlab-research/mask-attention-free-transformer/maft/utils/mask_encoder.py official repository ran no licence file found · pointer only · f8eff0243802706a · report
rle_encode dvlab-research/mask-attention-free-transformer/maft/utils/mask_encoder.py official repository ran no licence file found · pointer only · 6fdabd36a13625dd · report
scale_points dvlab-research/mask-attention-free-transformer/maft/model/pc_util.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · c2546a46c7f63930 · report
shift_scale_points dvlab-research/mask-attention-free-transformer/maft/model/pc_util.py official repository ran · fixture could not drive it no licence file found · pointer only · 818099bdffc93897 · report
batch_dice_loss dvlab-research/mask-attention-free-transformer/maft/model/loss.py official repository unverified no licence file found · pointer only · 89f8d423e0baf041 · report
batch_sigmoid_bce_loss dvlab-research/mask-attention-free-transformer/maft/model/loss.py official repository unverified no licence file found · pointer only · 2815d6704af5fb9c · report
batch_sigmoid_focal_loss dvlab-research/mask-attention-free-transformer/maft/model/loss.py official repository unverified no licence file found · pointer only · 5ce41ce149ac0278 · report
build_transformer dvlab-research/mask-attention-free-transformer/maft/model/transformer.py official repository unverified no licence file found · pointer only · 31be13e9daaa9da9 · report
multi_head_attention_forward dvlab-research/mask-attention-free-transformer/maft/model/attention.py official repository unverified no licence file found · pointer only · f09175b0f39f0ad0 · report
random_sampling dvlab-research/mask-attention-free-transformer/maft/model/pc_util.py official repository unverified no licence file found · pointer only · b91d93c29e979019 · report

Tasks

3D Instance SegmentationInstance SegmentationSemantic Segmentationregression

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Instance Segmentation ScanNet(v2) MAFT mAP 59.6 #32 of 32 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.

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