Edmund Lam — accepted AI-conference papers

2023

Context-Aware Transformer for 3D Point Cloud Automatic Annotation

Xiaoyan Qian, Chang Liu, Xiaojuan Qi, Siew-Chong Tan, Edmund Lam, Ngai Wong

AAAI 2023technical

3D automatic annotation has received increased attention since manually annotating 3D point clouds is laborious. However, existing methods are usually complicated, e.g., pipelined training for 3D foreground/background segmentation, cylindrical object proposals, and point completion. Furthermore, the…

Cited by 5 Source ↗PDF ↗Scholar ↗

2022

Multimodal Transformer for Automatic 3D Annotation and Object Detection

Chang Liu, Xiaoyan Qian, Binxiao Huang, Xiaojuan Qi, Edmund Lam, Siew-Chong Tan +1

ECCV 2022poster

"Despite a growing number of datasets being collected for training 3D object detection models, significant human effort is still required to annotate 3D boxes on LiDAR scans. To automate the annotation and facilitate the production of various customized datasets, we propose an end-to-end multimodal…

Cited by 13 Source ↗PDF ↗code ↗Scholar ↗