mlsanityData to 14 Oct 2026

FMOcc: TPV-Driven Flow Matching for 3D Occupancy Prediction with Selective State Space Model

arXiv 2507.02250 ↗First posted 3 Jul 2025cs.CVcited by 0

On the map: State-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing

Abstract (arXiv)

3D semantic occupancy prediction plays a pivotal role in autonomous driving. However, inherent limitations of fewframe images and redundancy in 3D space compromise prediction accuracy for occluded and distant scenes. Existing methods enhance performance by fusing historical frame data, which need additional data and significant computational resources. To address these issues, this paper propose FMOcc, a Tri-perspective View (TPV) refinement occupancy network with flow matching selective state space model for few-frame 3D occupancy prediction. Firstly, to generate missing features, we designed a feature refinement module based on a flow matching model, which is called Flow Matching SSM module (FMSSM). Furthermore, by designing the TPV SSM layer and Plane Selective SSM (PS3M), we selectively filter TPV features to reduce the impact of air voxels on non-air voxels, thereby enhancing the overall efficiency of the model and prediction capability for distant scenes. Finally, we design the Mask Training (MT) method to enhance the robustness of FMOcc and address the issue of sensor data loss. Experimental results on the Occ3D-nuScenes and OpenOcc datasets show that our FMOcc outperforms existing state-of-theart methods. Our FMOcc with two frame input achieves notable scores of 43.1% RayIoU and 39.8% mIoU on Occ3D-nuScenes validation, 42.6% RayIoU on OpenOcc with 5.4 G inference memory and 330ms inference time.

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 36 of its 46 references that are in the map. First posted on arXiv 3 Jul 2025.

Builds on

36 of 46 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024OccMamba: Semantic Occupancy Prediction with State Space Models19 Aug
  2. 2024Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection15 Jun

Other references · 34

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2022Flow Matching for Generative Modelingcited by 5,702
  5. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  6. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  7. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  8. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  9. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
  10. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,290
  11. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,056
  12. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 713
22 more
  1. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 409
  2. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 363
  3. 2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
  4. 2023Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Drivingcited by 332
  5. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 313
  6. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 293
  7. 2024LocalMamba: Visual State Space Model with Windowed Selective Scancited by 236
  8. 2023Scene as Occupancycited by 209
  9. 2021Diffusion Models for Implicit Image Segmentation Ensemblescited by 198
  10. 2023DDP: Diffusion Model for Dense Visual Predictioncited by 148
  11. 2023PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentationcited by 115
  12. 2023COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Predictioncited by 96
  13. 2023Monocular Depth Estimation using Diffusion Modelscited by 87
  14. 2023Fully Sparse 3D Occupancy Predictioncited by 64
  15. 2024OPUS: Occupancy Prediction Using a Sparse Setcited by 56
  16. 2024Co-Occ: Coupling Explicit Feature Fusion with Volume Rendering Regularization for Multi-Modal 3D Semantic Occupancy Predictioncited by 48
  17. 2023DiffBEV: Conditional Diffusion Model for Bird's Eye View Perceptioncited by 30
  18. 2024OccGen: Generative Multi-modal 3D Occupancy Prediction for Autonomous Drivingcited by 29
  19. 2023UniOcc: Unifying Vision-Centric 3D Occupancy Prediction with Geometric and Semantic Renderingcited by 26
  20. 2025STCOcc: Sparse Spatial-Temporal Cascade Renovation for 3D Occupancy and Scene Flow Predictioncited by 23
  21. 2024GEOcc: Geometrically Enhanced 3D Occupancy Network with Implicit-Explicit Depth Fusion and Contextual Self-Supervisioncited by 21
  22. 2024DifFUSER: Diffusion Model for Robust Multi-Sensor Fusion in 3D Object Detection and BEV Segmentationcited by 18

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation
  2. 2025OccLE: Label-Efficient 3D Semantic Occupancy Prediction
  3. 2024An Efficient Occupancy World Model via Decoupled Dynamic Flow and Image-assisted Training
  4. 2024MambaOcc: Visual State Space Model for BEV-based Occupancy Prediction with Local Adaptive Reordering
  5. 2024FSF-Net: Enhance 4D Occupancy Forecasting with Coarse BEV Scene Flow for Autonomous Driving
  6. 2026Dr.Occ: Depth- and Region-Guided 3D Occupancy from Surround-View Cameras for Autonomous Driving
  7. 2023Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications
  8. 2024Fast Occupancy Network