Weichao Qiu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Weichao Qiu has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Chunyu Wang
Microsoft Research Asia, Beijing, China
2 shared publications - Wenhu Qin
School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China
2 shared publications - Wenjun Zeng
Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative, Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, Zhejiang, China
2 shared publications - Zhe Zhang
School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China
2 shared publications
Latest Publications
- 16 November 2020
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 129 (3) , 703-718
AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild
- 16 November 2020
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 129 (3) , 703-718
AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild
- Open Access
AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild
Occlusion is probably the biggest challenge for human pose estimation in the wild. Typical solutions often rely on intrusive sensors such as IMUs to detect occluded joints. To make the task truly unconstrained, we present AdaFuse, an adaptive multiview fusion method, which can enhance the features in occluded views by leveraging those in visible views. The core of AdaFuse is to determine the point-point correspondence between two views which we solve effectively by exploring the sparsity of the heatmap representation. We also learn an adaptive fusion weight for each camera view to reflect its feature quality in order to reduce the chance that good features are undesirably corrupted by ``bad'' views. The fusion model is trained end-to-end with the pose estimation network, and can be directly applied to new camera configurations without additional adaptation. We extensively evaluate the approach on three public datasets including Human3.6M, Total Capture and CMU Panoptic. It outperforms the state-of-the-arts on all of them. We also create a large scale synthetic dataset Occlusion-Person, which allows us to perform numerical evaluation on the occluded joints, as it provides occlusion labels for every joint in the images. The dataset and code are released at https://github.com/zhezh/adafuse-3d-human-pose.
Open AccessAdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild
Occlusion is probably the biggest challenge for human pose estimation in the wild. Typical solutions often rely on intrusive sensors such as IMUs to detect occluded joints. To make the task truly unconstrained, we present AdaFuse, an adaptive multiview fusion method, which can enhance the features in occluded views by leveraging those in visible views. The core of AdaFuse is to determine the point-point correspondence between two views which we solve effectively by exploring the sparsity of the heatmap representation. We also learn an adaptive fusion weight for each camera view to reflect its feature quality in order to reduce the chance that good features are undesirably corrupted by ``bad'' views. The fusion model is trained end-to-end with the pose estimation network, and can be directly applied to new camera configurations without additional adaptation. We extensively evaluate the approach on three public datasets including Human3.6M, Total Capture and CMU Panoptic. It outperforms the state-of-the-arts on all of them. We also create a large scale synthetic dataset Occlusion-Person, which allows us to perform numerical evaluation on the occluded joints, as it provides occlusion labels for every joint in the images. The dataset and code are released at https://github.com/zhezh/adafuse-3d-human-pose.