4 papers
RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding
Hang Ji, Tao Ni, Xufeng Huang +4
This technical report introduces a targeted improvement to the StreamPETR framework, specifically aimed at enhancing velocity estimation, a critical factor influencing the overall…
MV-DETR: Multi-modality indoor object detection by Multi-View DEtecton TRansformers
Zichao Dong, Yilin Zhang, Xufeng Huang +4
We introduce a novel MV-DETR pipeline which is effective while efficient transformer based detection method. Given input RGBD data, we notice that there are super strong pretrainin…
LVIC: Multi-modality segmentation by Lifting Visual Info as Cue
Zichao Dong, Bowen Pang, Xufeng Huang +3
Multi-modality fusion is proven an effective method for 3d perception for autonomous driving. However, most current multi-modality fusion pipelines for LiDAR semantic segmentation…
PeP: a Point enhanced Painting method for unified point cloud tasks
Zichao Dong, Hang Ji, Xufeng Huang +3
Point encoder is of vital importance for point cloud recognition. As the very beginning step of whole model pipeline, adding features from diverse sources and providing stronger fe…