-
Leveraging Vision-Centric Multi-Modal Expertise for 3D Object Detection. NeurIPS 2023 [Official Code]
-
BEVSimDet: Simulated Multi-modal Distillation in Bird's-Eye View for Multi-view 3D Object Detection. Arxiv 2023 [Official Code]
-
Distilling Focal Knowledge From Imperfect Expert for 3D Object Detection. CVPR 2023 [Official Code]
-
UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye View. CVPR 2023 [Official Code]
-
X
$^3$ KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection. CVPR 2023 -
BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection. ICLR 2023 [Official Code]
-
BEV-LGKD: A Unified LiDAR-Guided Knowledge Distillation Framework for BEV 3D Object Detection. Arxiv 2022
-
TiG-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning. Arxiv 2022 [Official Code]
-
Structured Knowledge Distillation Towards Efficient and Compact Multi-View 3D Detection. Arxiv 2022
-
Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detection. ECCV 2022 [Official Code]
-
Lidar Point Cloud Guided Monocular 3D Object Detection. ECCV 2022 [Official Code]
-
LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector. ICCV 2021 [Official Code]
-
Representation Disparity-aware Distillation for 3D Object Detection. ICCV 2023
-
itKD: Interchange Transfer-based Knowledge Distillation for 3D Object Detection. CVPR 2023
-
PointDistiller: Structured Knowledge Distillation TowardsEfficient and Compact 3D Detection. CVPR 2023 [Official Code]
-
UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye View. CVPR 2023 [Official Code]
-
Towards Efficient 3D Object Detection withKnowledge Distillation. NeurIPS 2022 [Official Code]
-
LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection. ECCV 2022 [Official Code]
-
Geometric-aware Pretraining for Vision-centric 3D Object Detection. Arxiv 2023 [Official Code]
-
Towards Better 3D Knowledge Transfer via Masked Image Modeling for Multi-view 3D Understanding. ICCV 2023 [Official Code]
-
Segment Any Point Cloud Sequences by Distilling Vision Foundation Models. NeurIPS 2023 [Official Code]
-
Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data. CVPR 2022 [Official Code]
- Unsupervised 3D Perception with 2D Vision-Language Distillation for Autonomous Driving. ICCV 2023
Note: All papers' pdf can be found and downloaded on arXiv, Google or Bing.