WWWentao Wang

Wentao Wang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Wentao Wang has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Diverse image inpainting with disentangled uncertainty

    by Wentao Wang, Lu He, Li Niu, Jianfu Zhang, Yue Liu, Haoyu Ling, Liqing Zhang


  • Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalization

    by Xue Yang, Gefan Zhang, Xiaojiang Yang, Yue Zhou, Wentao Wang, Jin Tang, Tao He, Junchi Yan

    Existing detection methods commonly use a parameterized bounding box (BBox) to model and detect (horizontal) objects and an additional rotation angle parameter is used for rotated objects. We argue that such a mechanism has fundamental limitations in building an effective regression loss for rotation detection, especially for high-precision detection with high IoU (e.g. 0.75). Instead, we propose to model the rotated objects as Gaussian distributions. A direct advantage is that our new regression loss regarding the distance between two Gaussians e.g. Kullback-Leibler Divergence (KLD), can well align the actual detection performance metric, which is not well addressed in existing methods. Moreover, the two bottlenecks i.e. boundary discontinuity and square-like problem also disappear. We also propose an efficient Gaussian metric-based label assignment strategy to further boost the performance. Interestingly, by analyzing the BBox parameters' gradients under our Gaussian-based KLD loss, we show that these parameters are dynamically updated with interpretable physical meaning, which help explain the effectiveness of our approach, especially for high-precision detection. We extend our approach from 2-D to 3-D with a tailored algorithm design to handle the heading estimation, and experimental results on twelve public datasets (2-D/3-D, aerial/text/face images) with various base detectors show its superiority.


  • Image Editing via Segmentation Guided Self-Attention Network

    by Jianfu Zhang, Peiming Yang, Wentao Wang, Yan Hong, Liqing Zhang

    Image editing is one of the most popular directions in computer vision. Recently, many methods have benefited from the advances in deep learning, showing promising performance in the image editing task by inpainting the editing areas. These methods take advantage of edge information as user guidance to generate the desired content. However, they are suffering from generating color discrepancy and inconsistent boundaries. In this letter, we propose a deep image editing method based on a self-attention network which copies information for each of the small patches from distant spatial locations. The proposed method smooths the image, computes segmentation maps, and utilizes the segmentation information for guiding the self-attention layers to explicitly leverage image features from surrounding areas with similar appearances. Experimental results show that the proposed method achieves better performance, is flexible for different purposes, and fast for implementation.