Kang Zhang

Kang Zhang


Research Focus & Metrics

Academic Career Length

25Years (2002-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 December 2022 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
ZWZhiliang Wu
Zhiliang Wu
CSChangchang Sun
Changchang Sun
HXHanyu Xuan
Hanyu Xuan
KZKang Zhang
Kang Zhang
YYYan Yan
Yan Yan
Video inpainting aims to utilize plausible contents to complete missing regions in the video. For different components, the reconstruction targets of missing regions are different, e.g ., smoothness preserving for flat regions, sharpening for edges and textures. Typically, existing methods treat the missing regions as a whole and holistically train the model by optimizing homogenous pixel-wise losses ( e.g ., MSE). In this way, the trained models will be easily dominated and determined by flat regions, failing to infer realistic details (edges and textures) that are difficult to reconstruct but necessary for practical applications. In this paper, we propose a divide-and-conquer completion network for video inpainting. In particular, our network first uses discrete wavelet transform to decompose the deep features into low-frequency components containing structural information (flat regions) and high-frequency components involving detailed texture information. Thereafter, we feed these components into different branches and adopt the temporal attention feature aggregation module to generate missing contents, separately. It hence can realize flexible supervision utilizing the intermediate supervision learning strategy for each component, which has not been noticed and explored by current state-of-the-art video inpainting methods. Furthermore, we adopt a gradient-weighted reconstruction loss to supervise the completed frame reconstruction process, which can use the gradients in all directions of the video frame to emphasize the difficultly reconstructed textures regions, making the model pay more attention to the complex detailed textures. Extensive experiments validate the superior performance of our divide-and-conquer model over state-of-the-art baselines in both quantitative and qualitative evaluations.

3 June 2021 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
ZWZhiliang Wu
Zhiliang Wu
KZKang Zhang
Kang Zhang
HXHanyu Xuan
Hanyu Xuan
JYJian Yang
Jian Yang
YYYan Yan
Yan Yan
Video inpainting aims to fill missing regions with plausible content in a video sequence. Deep learning-based video inpainting methods have made promising progress over the past few years. However, these methods tend to generate degraded completion content, such as missing textural details. To address this issue, we propose a novel Deformable Alignment and Pyramid-context Completion Network for video inpainting (DAPC-Net), which takes advantage of temporal redundancy information among video sequence. Specifically, we construct a deformable convolution alignment network (DANet) for aligning reference frame at the feature level. After alignment, we further devise a pyramid-context completion network (PCNet) to complete missing regions of the target frame. Particularly, the pyramid completion mechanism and cross-scale transference strategy are used to ensure the visual and semantic coherence of the completed target frame. Experimental results show that the proposed method not only achieves better quantitative and qualitative performance but also improves the inference speed by 35.4%.

25 April 2023 in Signal Processing: Image Communication
Verified
Journal Article
Closed access
ZWZhiliang Wu
Zhiliang Wu
KZKang Zhang
Kang Zhang
HXHanyu Xuan
Hanyu Xuan
XYXia Yuan
Xia Yuan
CZChunxia Zhao
Chunxia Zhao

18 November 2021 in IET Image Processing
Verified
Journal Article
Open access
PDF file
KZKang Zhang
Kang Zhang
ZWZhiliang Wu
Zhiliang Wu
XYXia Yuan
Xia Yuan
CZChunxia Zhao
Chunxia Zhao
Multi‐focus image fusion aims to generate a clear image by fusing multiple source images. Existing deep learning‐based fusion methods often neglect the context information resulting in the loss of detail information. To address this issue, a context fusion network to merge multi‐focus images, namely CFNet, is proposed. Specifically, a context fusion module is proposed to make full use of low‐level pixels and high‐level semantic features. Particularly, the pyramid fusion mechanism and cross‐scale transfer strategy are adopted to ensure the visual and semantic consistency of the fused image. Meanwhile, to extract salient features more effectively, a spatial attention mechanism is introduced to enhance these features. Further, the pyramid loss is used to progressively refine the fused features at each scale. Experimental results show that the proposed method is superior to some existing methods in both qualitative and quantitative evaluation.

1 December 2009 in Journal of Visual Languages & Computing
Verified
Journal Article
Closed access
PKPushpa Kumar
Pushpa Kumar
KZKang Zhang
Kang Zhang

17 December 2002
Verified
Conference Paper
Closed access
KZKang Zhang
Kang Zhang
WMWanli Ma
Wanli Ma