MMDistill: Multi-Modal BEV Distillation Framework for Multi-View 3D Object Detection
Source abstract
Abstract
Multi-modal 3D object detection has achieved remarkable progress, but it is often limited in practical industrial production because of its high cost and low efficiency. The multi-view camera-based method provides a feasible ... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Industrial Vision Systems and Defect Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (41)
Show source-provided references
1. LiDAR-camera fusion in perspective view for 3D object detection in surface mine10.1109/TIV.2023.3343377 ↗
2. MFF-Net: Multimodal feature fusion network for 3D object detection
3. When object detection meets knowledge distillation: A survey10.1109/TPAMI.2023.3257546 ↗
4. Lightweight diffusion models: A survey10.1007/s10462-024-10800-8 ↗
5. BEVDepth: Acquisition of reliable depth for multi-view 3D object detection
6. MonoDistill: Learning spatial features for monocular 3D object detection
7. Unifying voxel-based representation with transformer for 3D object detection
8. Viewpoint equivariance for multi-view 3D object detection
9. UniFusion: Unified multi-view fusion transformer for spatial-temporal representation in bird’s-eye-view
10. BEVFormer: Learning bird’s-eye-view representation from multi-camera images via spatiotemporal transformers
11. What makes multi-modal learning better than single (provably)
12. Multi-view 3D object detection network for autonomous driving
13. BEVFusion: Multi-task multi-sensor fusion with unified bird’s-eye view representation
14. FUTR3D: A unified sensor fusion framework for 3D detection
15. Multi-modal 3D object detection in autonomous driving: A survey and taxonomy10.1109/TIV.2023.3264658 ↗
16. Multi-level knowledge distillation for low resolution object detection and facial expression recognition10.1016/j.knosys.2022.108136 ↗
17. IDA-DET: An information discrepancy aware distillation for 1-bit detectors
18. Focal and global knowledge distillation for detectors
19. DistillBEV: Boosting multi-camera 3D object detection with cross-modal knowledge distillation
20. SimDistill: Simulated multi-modal distillation for BEV 3D object detection
21. X3KD: Knowledge distillation across modalities, tasks and stages for multi-camera 3D object detection
22. EfficientNet: Rethinking model scaling for convolutional neural networks
23. Object DGCNN: 3D object detection using dynamic graphs
24. PointPillars: Fast encoders for object detection from point clouds
25. nuScenes: A multi-modal dataset for autonomous driving
26. Decoupled weight decay regularization
27. J. Huang, G. Huang, Z. Zhu, Y. Ye, and D. Du, “BEVDet: High-performance multi-camera 3D object detection in bird-eye-view,” 2021, arXiv:2112.11790.
28. FCOS3D: Fully convolutional one-stage monocular 3D object detection
29. Z. Wang et al., “STS: Surround-view temporal stereo for multi-view 3D detection,” 2022, arXiv:2208.10145.
30. DETR3D: 3D object detection from multi-view images via 3D-to-2D queries
31. PETR: Position embedding transformation for multi-view 3D object detection
32. P. Huang et al., “TiG-BEV: Multi-view BEV 3D object detection via target inner-geometry learning,” 2022, arXiv:2212.13979.
33. Are we ready for autonomous driving? The kitti vision benchmark suite
34. PV-RCNN++: Point-voxel feature set abstraction with local vector representation for 3D object detection10.1007/s11263-022-01710-9 ↗
35. Spatial information enhancement network for 3D object detection from point cloud10.1016/j.patcog.2022.108684 ↗
36. Homogeneous multi-modal feature fusion and interaction for 3D object detection
37. 3D-CVF: Generating joint camera and LiDAR features using cross-view spatial feature fusion for 3D object detection
38. VoPiFNet: Voxel-pixel fusion network for multi-class 3D object detection10.1109/TITS.2024.3392783 ↗
39. PointPainting: Sequential fusion for 3D object detection
40. RCM-Fusion: Radar-camera multi-level fusion for 3D object detection
41. P. Wolters et al., “Unleashing hyDRa: Hybrid fusion, depth consistency and radar for unified 3D perception,” 2024, arXiv:2403.07746.