HybridTM: Combining Transformer and Mamba for 3D Semantic Segmentation
On the map: State-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
Abstract (arXiv)
Transformer-based methods have demonstrated remarkable capabilities in 3D semantic segmentation through their powerful attention mechanisms, but the quadratic complexity limits their modeling of long-range dependencies in large-scale point clouds. While recent Mamba-based approaches offer efficient processing with linear complexity, they struggle with feature representation when extracting 3D features. However, effectively combining these complementary strengths remains an open challenge in this field. In this paper, we propose HybridTM, the first hybrid architecture that integrates Transformer and Mamba for 3D semantic segmentation. In addition, we propose the Inner Layer Hybrid Strategy, which combines attention and Mamba at a finer granularity, enabling simultaneous capture of long-range dependencies and fine-grained local features. Extensive experiments demonstrate the effectiveness and generalization of our HybridTM on diverse indoor and outdoor datasets. Furthermore, our HybridTM achieves state-of-the-art performance on ScanNet, ScanNet200, and nuScenes benchmarks. The code will be made available at https://github.com/deepinact/HybridTM.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Point clouds, detection and remote sensing, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 41 of its 51 references that are in the map. First posted on arXiv 24 Jul 2025.
Builds on
41 of 51 references.
Closest ancestors · 5
Same direction, newest first
- 2024LION: Linear Group RNN for 3D Object Detection in Point Clouds25 Jul
- 2024Serialized Point Mamba: A Serialized Point Cloud Mamba Segmentation Model17 Jul
- 2024Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategy11 Mar
- 2024MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small Target Detection4 Mar
- 2024Point Cloud Mamba: Point Cloud Learning via State Space Model1 Mar
Other references · 36
- 2017Attention Is All You Needcited by 60,361
- 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
- 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
- 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
- 2020Point Transformercited by 1,470
- 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 1,336
- 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
- 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,056
- 2024VMamba: Visual State Space Modelcited by 969
- 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
- 2020PCT: Point cloud transformercited by 732
24 more
- 2023Point Transformer V3: Simpler, Faster, Strongercited by 589
- 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 436
- 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 423
- 2024Jamba: A Hybrid Transformer-Mamba Language Modelcited by 401
- 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 389
- 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 388
- 2024VM-UNet: Vision Mamba UNet for Medical Image Segmentationcited by 287
- 2024LocalMamba: Visual State Space Model with Windowed Selective Scancited by 236
- 2024MambaVision: A Hybrid Mamba-Transformer Vision Backbonecited by 224
- 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 167
- 2021(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Networkcited by 164
- 2024EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mambacited by 146
- 2023Spherical Transformer for LiDAR-based 3D Recognitioncited by 125
- 2023Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understandingcited by 113
- 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 109
- 2021Fast Point Transformercited by 104
- 2021EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detectioncited by 49
- 2024Hydra: Bidirectional State Space Models Through Generalized Matrix Mixerscited by 44
- 2021PatchFormer: An Efficient Point Transformer with Patch Attentioncited by 43
- 2022Gaussian Radar Transformer for Semantic Segmentation in Noisy Radar Datacited by 15
- 2024MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretrainingcited by 12
- 2024MaskMamba: A Hybrid Mamba-Transformer Model for Masked Image Generationcited by 8
- 2019Multi-view Incremental Segmentation of 3D Point Clouds for Mobile Robotscited by 4
- 2024OMEGA: Efficient Occlusion-Aware Navigation for Air-Ground Robot in Dynamic Environments via State Space Modelcited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Exploring contextual modeling with linear complexity for point cloud segmentation
- 2025HybridMamba: A Dual-domain Mamba for 3D Medical Image Segmentation
- 2026Generalizing Geometry-Guided Mamba as a Plug-and-Play Context Module for CNN-based Semantic Segmentation
- 2026Breaking the Resource Wall: Geometry-Guided Sequence Modeling for Efficient Semantic Segmentation
- 2025Hybrid Transformer-Mamba for Weakly Supervised Volumetric Medical Segmentation
- 2025ECMNet:Lightweight Semantic Segmentation with Efficient CNN-Mamba Network
- 2024Pamba: Enhancing Global Interaction in Point Clouds via State Space Model
- 2025Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentation