# Mask4Former: Mask Transformer for 4D Panoptic Segmentation

arXiv: https://arxiv.org/abs/2309.16133 · HTML: https://mlsanity.com/paper/2309.16133/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 62 references that are in the map.
- First posted on arXiv 28 Sep 2023.

## Builds on (most cited first, 30 of 41)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://mlsanity.com/paper/1912.13192/) (2019)
- [Panoptic Segmentation](https://mlsanity.com/paper/1801.00868/) (2018)
- [Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution](https://mlsanity.com/paper/2007.16100/) (2020)
- [Video Instance Segmentation](https://mlsanity.com/paper/1905.04804/) (2019)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation](https://mlsanity.com/paper/2011.10033/) (2020)
- [PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation](https://mlsanity.com/paper/2004.01658/) (2020)
- [MOTS: Multi-Object Tracking and Segmentation](https://mlsanity.com/paper/1902.03604/) (2019)
- [SoftGroup for 3D Instance Segmentation on Point Clouds](https://mlsanity.com/paper/2203.01509/) (2022)
- [Tangent Convolutions for Dense Prediction in 3D](https://mlsanity.com/paper/1807.02443/) (2018)
- [Mask2Former for Video Instance Segmentation](https://mlsanity.com/paper/2112.10764/) (2021)
- [Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Tracking](https://mlsanity.com/paper/2109.03805/) (2021)
- [3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation](https://mlsanity.com/paper/2003.13867/) (2020)
- [Superpoint Transformer for 3D Scene Instance Segmentation](https://mlsanity.com/paper/2211.15766/) (2022)
- [Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation](https://mlsanity.com/paper/2103.14962/) (2021)
- [Just Go with the Flow: Self-Supervised Scene Flow Estimation](https://mlsanity.com/paper/1912.00497/) (2019)
- [LiDAR-based Panoptic Segmentation via Dynamic Shifting Network](https://mlsanity.com/paper/2011.11964/) (2020)
- [EfficientLPS: Efficient LiDAR Panoptic Segmentation](https://mlsanity.com/paper/2102.08009/) (2021)

## Built on by (most cited first, 24 of 24)

- [DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation](https://mlsanity.com/paper/2503.18944/) (2025)
- [JRDB-PanoTrack: An Open-world Panoptic Segmentation and Tracking Robotic Dataset in Crowded Human Environments](https://mlsanity.com/paper/2404.01686/) (2024)
- [Spotting the Unexpected (STU): A 3D LiDAR Dataset for Anomaly Segmentation in Autonomous Driving](https://mlsanity.com/paper/2505.02148/) (2025)
- [Self-supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural Calibration](https://mlsanity.com/paper/2401.12452/) (2024)
- [Zero-Shot 4D Lidar Panoptic Segmentation](https://mlsanity.com/paper/2504.00848/) (2025)
- [DoppDrive: Doppler-Driven Temporal Aggregation for Improved Radar Object Detection](https://mlsanity.com/paper/2508.12330/) (2025)
- [SegNet4D: Efficient Instance-Aware 4D Semantic Segmentation for LiDAR Point Cloud](https://mlsanity.com/paper/2406.16279/) (2024)
- [Interactive4D: Interactive 4D LiDAR Segmentation](https://mlsanity.com/paper/2410.08206/) (2024)
- [SALT: A Flexible Semi-Automatic Labeling Tool for General LiDAR Point Clouds with Cross-Scene Adaptability and 4D Consistency](https://mlsanity.com/paper/2503.23980/) (2025)
- [Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding](https://mlsanity.com/paper/2604.19609/) (2026)
- [TrackOcc: Camera-based 4D Panoptic Occupancy Tracking](https://mlsanity.com/paper/2503.08471/) (2025)
- [Relative Energy Learning for LiDAR Out-of-Distribution Detection](https://mlsanity.com/paper/2511.06720/) (2025)
- [ReScene4D: Temporally Consistent Semantic Instance Segmentation of Evolving Indoor 3D Scenes](https://mlsanity.com/paper/2601.11508/) (2026)
- [Panoptic-CUDAL: Rural Australia Point Cloud Dataset in Rainy Conditions](https://mlsanity.com/paper/2503.16378/) (2025)
- [To New Beginnings: A Survey of Unified Perception in Autonomous Vehicle Software](https://mlsanity.com/paper/2508.20892/) (2025)
- [D-PLS: Decoupled Semantic Segmentation for 4D-Panoptic-LiDAR-Segmentation](https://mlsanity.com/paper/2501.15870/) (2025)
- [SNAP: Towards Segmenting Anything in Any Point Cloud](https://mlsanity.com/paper/2510.11565/) (2025)
- [4DSegStreamer: Streaming 4D Panoptic Segmentation via Dual Threads](https://mlsanity.com/paper/2510.17664/) (2025)
- [Canonical Space Representation for 4D Panoptic Segmentation of Articulated Objects](https://mlsanity.com/paper/2511.05356/) (2025)
- [ASSIST-3D: Adapted Scene Synthesis for Class-Agnostic 3D Instance Segmentation](https://mlsanity.com/paper/2512.09364/) (2025)
- [Training-Free Global Geometric Association for 4D LiDAR Panoptic Segmentation](https://mlsanity.com/paper/2512.18991/) (2025)
- [Neural Distribution Prior for LiDAR Out-of-Distribution Detection](https://mlsanity.com/paper/2604.09232/) (2026)
- [Learning to Identify Out-of-Distribution Objects for 3D LiDAR Anomaly Segmentation](https://mlsanity.com/paper/2604.23604/) (2026)
- [Bootstrapping a 4D LiDAR Annotation Tool from Video Foundation Models](https://mlsanity.com/paper/2608.25418/) (2026)

## Abstract (arXiv)

Accurately perceiving and tracking instances over time is essential for the decision-making processes of autonomous agents interacting safely in dynamic environments. With this intention, we propose Mask4Former for the challenging task of 4D panoptic segmentation of LiDAR point clouds. Mask4Former is the first transformer-based approach unifying semantic instance segmentation and tracking of sparse and irregular sequences of 3D point clouds into a single joint model. Our model directly predicts semantic instances and their temporal associations without relying on hand-crafted non-learned association strategies such as probabilistic clustering or voting-based center prediction. Instead, Mask4Former introduces spatio-temporal instance queries that encode the semantic and geometric properties of each semantic tracklet in the sequence. In an in-depth study, we find that promoting spatially compact instance predictions is critical as spatio-temporal instance queries tend to merge multiple semantically similar instances, even if they are spatially distant. To this end, we regress 6-DOF bounding box parameters from spatio-temporal instance queries, which are used as an auxiliary task to foster spatially compact predictions. Mask4Former achieves a new state-of-the-art on the SemanticKITTI test set with a score of 68.4 LSTQ.