# DQFormer: Towards Unified LiDAR Panoptic Segmentation with Decoupled Queries

arXiv: https://arxiv.org/abs/2408.15813 · HTML: https://mlsanity.com/paper/2408.15813/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 58 references that are in the map.
- First posted on arXiv 28 Aug 2024.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [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)
- [Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution](https://mlsanity.com/paper/2007.16100/) (2020)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation](https://mlsanity.com/paper/2011.10033/) (2020)
- [K-Net: Towards Unified Image Segmentation](https://mlsanity.com/paper/2106.14855/) (2021)
- [Embracing Single Stride 3D Object Detector with Sparse Transformer](https://mlsanity.com/paper/2112.06375/) (2021)
- [Spherical Transformer for LiDAR-based 3D Recognition](https://mlsanity.com/paper/2303.12766/) (2023)
- [Seamless Scene Segmentation](https://mlsanity.com/paper/1905.01220/) (2019)
- [Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers](https://mlsanity.com/paper/2109.03814/) (2021)
- [CenterFormer: Center-based Transformer for 3D Object Detection](https://mlsanity.com/paper/2209.05588/) (2022)
- [LiDAR-based Panoptic Segmentation via Dynamic Shifting Network](https://mlsanity.com/paper/2011.11964/) (2020)
- [DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution](https://mlsanity.com/paper/2011.13328/) (2020)
- [Panoptic-PHNet: Towards Real-Time and High-Precision LiDAR Panoptic Segmentation via Clustering Pseudo Heatmap](https://mlsanity.com/paper/2205.07002/) (2022)
- [MOPT: Multi-Object Panoptic Tracking](https://mlsanity.com/paper/2004.08189/) (2020)
- [Panoster: End-to-end Panoptic Segmentation of LiDAR Point Clouds](https://mlsanity.com/paper/2010.15157/) (2020)
- [A Benchmark for LiDAR-based Panoptic Segmentation based on KITTI](https://mlsanity.com/paper/2003.02371/) (2020)
- [GP-S3Net: Graph-based Panoptic Sparse Semantic Segmentation Network](https://mlsanity.com/paper/2108.08401/) (2021)
- [3D Instances as 1D Kernels](https://mlsanity.com/paper/2207.07372/) (2022)
- [Sparse Cross-scale Attention Network for Efficient LiDAR Panoptic Segmentation](https://mlsanity.com/paper/2201.05972/) (2022)
- [Position-Guided Point Cloud Panoptic Segmentation Transformer](https://mlsanity.com/paper/2303.13509/) (2023)
- [PUPS: Point Cloud Unified Panoptic Segmentation](https://mlsanity.com/paper/2302.06185/) (2023)
- [TransVOS: Video Object Segmentation with Transformers](https://mlsanity.com/paper/2106.00588/) (2021)
- [MaskRange: A Mask-classification Model for Range-view based LiDAR Segmentation](https://mlsanity.com/paper/2206.12073/) (2022)
- [CPSeg: Cluster-free Panoptic Segmentation of 3D LiDAR Point Clouds](https://mlsanity.com/paper/2111.01723/) (2021)
- [4D-Former: Multimodal 4D Panoptic Segmentation](https://mlsanity.com/paper/2311.01520/) (2023)

## Abstract (arXiv)

LiDAR panoptic segmentation, which jointly performs instance and semantic segmentation for things and stuff classes, plays a fundamental role in LiDAR perception tasks. While most existing methods explicitly separate these two segmentation tasks and utilize different branches (i.e., semantic and instance branches), some recent methods have embraced the query-based paradigm to unify LiDAR panoptic segmentation. However, the distinct spatial distribution and inherent characteristics of objects(things) and their surroundings(stuff) in 3D scenes lead to challenges, including the mutual competition of things/stuff and the ambiguity of classification/segmentation. In this paper, we propose decoupling things/stuff queries according to their intrinsic properties for individual decoding and disentangling classification/segmentation to mitigate ambiguity. To this end, we propose a novel framework dubbed DQFormer to implement semantic and instance segmentation in a unified workflow. Specifically, we design a decoupled query generator to propose informative queries with semantics by localizing things/stuff positions and fusing multi-level BEV embeddings. Moreover, a query-oriented mask decoder is introduced to decode corresponding segmentation masks by performing masked cross-attention between queries and mask embeddings. Finally, the decoded masks are combined with the semantics of the queries to produce panoptic results. Extensive experiments on nuScenes and SemanticKITTI datasets demonstrate the superiority of our DQFormer framework.