Heng Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Heng Li has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
Jamal Ahmed Rahim
Simon Fraser University
1 shared publication- Luwei Yang
Department of Electrical and Electronic Engineering, University of Hong Kong, Hong Kong Special Administrative Region, Hong Kong, China
1 shared publication - Ping Tan
Hong Kong University of Science and Technology
1 shared publication - Zhaopeng Cui
Zhejiang University
1 shared publication
Latest Publications
- 1 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 26, 11769-11778
End-to-End Rotation Averaging with Multi-Source Propagation
This paper presents an end-to-end neural network for multiple rotation averaging in SfM. Due to the manifold constraint of rotations, conventional methods usually take two separate steps involving spanning tree based initialization and iterative nonlinear optimization respectively. These methods can suffer from bad initializations due to the noisy spanning tree or outliers in input relative rotations. To handle these problems, we propose to integrate initialization and optimization together in an unified graph neural network via a novel differentiable multi-source propagation module. Specifically, our network utilizes the image context and geometric cues in feature correspondences to reduce the impact of outliers. Furthermore, unlike the methods that utilize the spanning tree to initialize orientations according to a single reference node in a top-down manner, our net-work initializes orientations according to multiple sources while utilizing information from all neighbors in a differentiable way. More importantly, our end-to-end formulation also enables iterative re-weighting of input relative orientations at test time to improve the accuracy of the final estimation by minimizing the impact of outliers. We demonstrate the effectiveness of our method on two real-world datasets, achieving state-of-the-art performance.
- 1 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 26, 11769-11778
End-to-End Rotation Averaging with Multi-Source Propagation
This paper presents an end-to-end neural network for multiple rotation averaging in SfM. Due to the manifold constraint of rotations, conventional methods usually take two separate steps involving spanning tree based initialization and iterative nonlinear optimization respectively. These methods can suffer from bad initializations due to the noisy spanning tree or outliers in input relative rotations. To handle these problems, we propose to integrate initialization and optimization together in an unified graph neural network via a novel differentiable multi-source propagation module. Specifically, our network utilizes the image context and geometric cues in feature correspondences to reduce the impact of outliers. Furthermore, unlike the methods that utilize the spanning tree to initialize orientations according to a single reference node in a top-down manner, our net-work initializes orientations according to multiple sources while utilizing information from all neighbors in a differentiable way. More importantly, our end-to-end formulation also enables iterative re-weighting of input relative orientations at test time to improve the accuracy of the final estimation by minimizing the impact of outliers. We demonstrate the effectiveness of our method on two real-world datasets, achieving state-of-the-art performance.