Ke Song
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ke Song has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Fanbin Gu
The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
1 shared publication - Huiyuan Xiong
Guangdong Provincial Key Laboratory of Intelligent Transportation System, School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China
1 shared publication - Jiangxia Chen
School of Artificial Intelligence Chongqing University of Technology 401135 Chongqing China
1 shared publication - Jingyuan Fan
The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
1 shared publication - Qingtang Zhu
Department of Microsurgery, Orthopedic Trauma and Hand Surgery, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
1 shared publication - Tongyuan Huang
School of Artificial Intelligence Chongqing University of Technology Chongqing China
1 shared publication
Latest Publications
- 11 September 2025
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 19 (13) , 1-12
MTFT: Multimodal Temporal Fusion Transformer for 3D Human Pose and Shape Estimation
- 11 September 2025
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 19 (13) , 1-12
MTFT: Multimodal Temporal Fusion Transformer for 3D Human Pose and Shape Estimation
- Open Access
FMOcc: TPV-Driven Flow Matching for 3D Occupancy Prediction with Selective State Space Model
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.
Open AccessFMOcc: TPV-Driven Flow Matching for 3D Occupancy Prediction with Selective State Space Model
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.