Tian Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Tian Chen has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Chao Ma
Shanghai Jiao Tong University
1 shared publication - Chongyang Ma
Kuaishou Technology, Beijing, China
1 shared publication - Han Yan
Shanghai Jiao Tong University, Shanghai, China
1 shared publication - Hongdong Li
School of Computing, Australian National University, Canberra, Australia
1 shared publication - Huayan Wang
Northwest A&F University
1 shared publication - Pan Ji
Tencent, Shanghai, China
1 shared publication
Latest Publications
- Open Access
- 3 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Frankenstein: Generating Semantic-Compositional 3D Scenes in One Tri-Plane
- 3 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessFrankenstein: Generating Semantic-Compositional 3D Scenes in One Tri-Plane
- Open Access
Improving Monocular Depth Estimation by Leveraging Structural Awareness and Complementary Datasets
Monocular depth estimation plays a crucial role in 3D recognition and understanding. One key limitation of existing approaches lies in their lack of structural information exploitation, which leads to inaccurate spatial layout, discontinuous surface, and ambiguous boundaries. In this paper, we tackle this problem in three aspects. First, to exploit the spatial relationship of visual features, we propose a structure-aware neural network with spatial attention blocks. These blocks guide the network attention to global structures or local details across different feature layers. Second, we introduce a global focal relative loss for uniform point pairs to enhance spatial constraint in the prediction, and explicitly increase the penalty on errors in depth-wise discontinuous regions, which helps preserve the sharpness of estimation results. Finally, based on analysis of failure cases for prior methods, we collect a new Hard Case (HC) Depth dataset of challenging scenes, such as special lighting conditions, dynamic objects, and tilted camera angles. The new dataset is leveraged by an informed learning curriculum that mixes training examples incrementally to handle diverse data distributions. Experimental results show that our method outperforms state-of-the-art approaches by a large margin in terms of both prediction accuracy on NYUDv2 dataset and generalization performance on unseen datasets.
Open AccessImproving Monocular Depth Estimation by Leveraging Structural Awareness and Complementary Datasets
Monocular depth estimation plays a crucial role in 3D recognition and understanding. One key limitation of existing approaches lies in their lack of structural information exploitation, which leads to inaccurate spatial layout, discontinuous surface, and ambiguous boundaries. In this paper, we tackle this problem in three aspects. First, to exploit the spatial relationship of visual features, we propose a structure-aware neural network with spatial attention blocks. These blocks guide the network attention to global structures or local details across different feature layers. Second, we introduce a global focal relative loss for uniform point pairs to enhance spatial constraint in the prediction, and explicitly increase the penalty on errors in depth-wise discontinuous regions, which helps preserve the sharpness of estimation results. Finally, based on analysis of failure cases for prior methods, we collect a new Hard Case (HC) Depth dataset of challenging scenes, such as special lighting conditions, dynamic objects, and tilted camera angles. The new dataset is leveraged by an informed learning curriculum that mixes training examples incrementally to handle diverse data distributions. Experimental results show that our method outperforms state-of-the-art approaches by a large margin in terms of both prediction accuracy on NYUDv2 dataset and generalization performance on unseen datasets.