|
Hao Luo is a master's student majoring in mechanical engineering from the School of Modern Post (School of Automation), Beijing University of Posts and Telecommunications, advised by Prof.Haibin Yan. He received his BS degree in mechanical engineering from the School of Modern Post (School of Automation), Beijing University of Posts and Telecommunications, Beijing, in 2022. His main research areas are computer vision and robotic manipulation. |
|
|
|
|
Hao Luo, Zhenyu Wu, Haibin Yan International Conference on Image and Graphics (ICIG), 2023 [PDF] We propose a framework named AE-Reorient actively explores the scene, allowing the robot to autonomously learn scene interaction strategies through reinforcement learning to search for target objects in clutter. |
|
Zhenyu Wu, Ziwei Wang, Shengyu Liu, Hao Luo, Jiwen Lu, and Haibin Yan preprint [PDF] In this paper, we propose an unbiased graph neural network learning method called FairScene for indoor scene synthesis, which can fully exploit unbiased object interactions through causal reasoning, so that fair scene synthesis is achieved by calibrating the long-tailed category distribution and eliminating the confounder effects. |
|
|
|
|
|
|