# Mask-Attention-Free Transformer for 3D Instance Segmentation

arXiv: https://arxiv.org/abs/2309.01692 · HTML: https://mlsanity.com/paper/2309.01692/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- Builds on 67 of its 76 references that are in the map.
- First posted on arXiv 4 Sep 2023.

## Builds on (most cited first, 30 of 67)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [PVT v2: Improved Baselines with Pyramid Vision Transformer](https://mlsanity.com/paper/2106.13797/) (2021)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR](https://mlsanity.com/paper/2201.12329/) (2022)
- [Twins: Revisiting the Design of Spatial Attention in Vision Transformers](https://mlsanity.com/paper/2104.13840/) (2021)
- [CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows](https://mlsanity.com/paper/2107.00652/) (2021)
- [DN-DETR: Accelerate DETR Training by Introducing Query DeNoising](https://mlsanity.com/paper/2203.01305/) (2022)
- [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021)
- [Point Transformer V2: Grouped Vector Attention and Partition-based Pooling](https://mlsanity.com/paper/2210.05666/) (2022)
- [Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation](https://mlsanity.com/paper/2206.02777/) (2022)
- [An End-to-End Transformer Model for 3D Object Detection](https://mlsanity.com/paper/2109.08141/) (2021)
- [PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation](https://mlsanity.com/paper/2004.01658/) (2020)
- [Focal Self-attention for Local-Global Interactions in Vision Transformers](https://mlsanity.com/paper/2107.00641/) (2021)
- [Language-Grounded Indoor 3D Semantic Segmentation in the Wild](https://mlsanity.com/paper/2204.07761/) (2022)
- [3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans](https://mlsanity.com/paper/1812.07003/) (2018)
- [Group-Free 3D Object Detection via Transformers](https://mlsanity.com/paper/2104.00678/) (2021)

## Built on by (most cited first, 30 of 46)

- [3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer](https://mlsanity.com/paper/2501.01163/) (2025)
- [Rank-DETR for High Quality Object Detection](https://mlsanity.com/paper/2310.08854/) (2023)
- [SegPoint: Segment Any Point Cloud via Large Language Model](https://mlsanity.com/paper/2407.13761/) (2024)
- [ODIN: A Single Model for 2D and 3D Segmentation](https://mlsanity.com/paper/2401.02416/) (2024)
- [RefMask3D: Language-Guided Transformer for 3D Referring Segmentation](https://mlsanity.com/paper/2407.18244/) (2024)
- [Spherical Mask: Coarse-to-Fine 3D Point Cloud Instance Segmentation with Spherical Representation](https://mlsanity.com/paper/2312.11269/) (2023)
- [3D-GRES: Generalized 3D Referring Expression Segmentation](https://mlsanity.com/paper/2407.20664/) (2024)
- [A Unified Framework for 3D Scene Understanding](https://mlsanity.com/paper/2407.03263/) (2024)
- [Unifying 2D and 3D Vision-Language Understanding](https://mlsanity.com/paper/2503.10745/) (2025)
- [SGIFormer: Semantic-guided and Geometric-enhanced Interleaving Transformer for 3D Instance Segmentation](https://mlsanity.com/paper/2407.11564/) (2024)
- [Grounding 3D Scene Affordance From Egocentric Interactions](https://mlsanity.com/paper/2409.19650/) (2024)
- [RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation](https://mlsanity.com/paper/2412.02402/) (2024)
- [Relation3D: Enhancing Relation Modeling for Point Cloud Instance Segmentation](https://mlsanity.com/paper/2506.17891/) (2025)
- [Uni3DL: Unified Model for 3D and Language Understanding](https://mlsanity.com/paper/2312.03026/) (2023)
- [Towards Scalable Spatial Intelligence via 2D-to-3D Data Lifting](https://mlsanity.com/paper/2507.18678/) (2025)
- [SAS: Segment Any 3D Scene with Integrated 2D Priors](https://mlsanity.com/paper/2503.08512/) (2025)
- [MoE3D: Mixture of Experts meets Multi-Modal 3D Understanding](https://mlsanity.com/paper/2511.22103/) (2025)
- [SymPoint Revolutionized: Boosting Panoptic Symbol Spotting with Layer Feature Enhancement](https://mlsanity.com/paper/2407.01928/) (2024)
- [Qwen-3D: A Generalist 3D Vision-Language Model for Spatial Understanding](https://mlsanity.com/paper/2608.02980/) (2026)
- [MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation](https://mlsanity.com/paper/2411.01781/) (2024)
- [CompetitorFormer: Competitor Transformer for 3D Instance Segmentation](https://mlsanity.com/paper/2411.14179/) (2024)
- [Sketchy Bounding-box Supervision for 3D Instance Segmentation](https://mlsanity.com/paper/2505.16399/) (2025)
- [PGOV3D: Open-Vocabulary 3D Semantic Segmentation with Partial-to-Global Curriculum](https://mlsanity.com/paper/2506.23607/) (2025)
- [SegDINO3D: 3D Instance Segmentation Empowered by Both Image-Level and Object-Level 2D Features](https://mlsanity.com/paper/2509.16098/) (2025)
- [OVSeg3R: Learn Open-vocabulary Instance Segmentation from 2D via 3D Reconstruction](https://mlsanity.com/paper/2509.23541/) (2025)
- [Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding](https://mlsanity.com/paper/2604.19609/) (2026)
- [Advancements in Point Cloud-Based 3D Defect Detection and Classification for Industrial Systems: A Comprehensive Survey](https://mlsanity.com/paper/2402.12923/) (2024)
- [SA3DIP: Segment Any 3D Instance with Potential 3D Priors](https://mlsanity.com/paper/2411.03819/) (2024)
- [Beyond the Final Layer: Hierarchical Query Fusion Transformer with Agent-Interpolation Initialization for 3D Instance Segmentation](https://mlsanity.com/paper/2502.04139/) (2025)
- [GrabS: Generative Embodied Agent for 3D Object Segmentation without Scene Supervision](https://mlsanity.com/paper/2504.11754/) (2025)

## Abstract (arXiv)

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.