Buyu Li is a PhD candidate at Multimedia Lab (MMLab), The Chinese University of Hong Kong, supervised by Prof. Xiaogang Wang. He also has a close research collaboration with Yu Liu, Quanquan Li, Junjie Yan and Prof. Wanli Ouyang.

He used to work as a computer vision researcher in Sensetime Research (2016-2017). During this period, he was a member of the CUImage team that won the first place in ILSVRC2016 DET (ImageNet).

His research interests now include but not limit to object detection (both 2D and 3D), and 3D animation.


  • Computer Vision
  • Computer Graphics
  • Machine Learning


  • PhD in EE, 2017-present

    The Chinese University of Hong Kong

  • BEng in EE, 2012-2016

    Tsinghua University

Recent Publications

Equalization Loss for Long-Tailed Object Recognition (CVPR 2020)

Object recognition techniques using convolutional neural networks (CNN) have achieved great success. However, state-of-the-art object …

Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimation (AAAI 2020)

Monocular 3D object detection task aims to predict the 3D bounding boxes of objects based on monocular RGB images. Since the location …

GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving (CVPR 2019)

We present an efficient 3D object detection framework based on a single RGB image in the scenario of autonomous driving. Our efforts …

Gradient Harmonized Single-stage Detector (AAAI 2019 Oral)

Despite the great success of two-stage detectors, single-stage detector is still a more elegant and efficient way, yet suffers from the …

Grid R-CNN (CVPR 2019)

This paper proposes a novel object detection framework named Grid R-CNN, which adopts a grid guided localization mechanism for accurate …