Ming Liu

Mr. Ming Liu


Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
1 June 2019
Verified
Conference Paper
Closed access
MLMing Liu
Ming Liu
YDYukang Ding
Yukang Ding
MXMin Xia
Min Xia
XLXiao Liu
Xiao Liu
EDErrui Ding
Errui Ding
SWShilei Wen
Shilei Wen
Arbitrary attribute editing generally can be tackled by incorporating encoder-decoder and generative adversarial networks. However, the bottleneck layer in encoder-decoder usually gives rise to blurry and low quality editing result. And adding skip connections improves image quality at the cost of weakened attribute manipulation ability. Moreover, existing methods exploit target attribute vector to guide the flexible translation to desired target domain. In this work, we suggest to address these issues from selective transfer perspective. Considering that specific editing task is certainly only related to the changed attributes instead of all target attributes, our model selectively takes the difference between target and source attribute vectors as input. Furthermore, selective transfer units are incorporated with encoder-decoder to adaptively select and modify encoder feature for enhanced attribute editing. Experiments show that our method (i.e., STGAN) simultaneously improves attribute manipulation accuracy as well as perception quality, and performs favorably against state-of-the-arts in arbitrary face attribute editing and season translation.

6 October 2018
Verified
Book Chapter
Closed access
PDF file
XLXiaoming Li
Xiaoming Li
MLMing Liu
Ming Liu
YYYuting Ye
Yuting Ye
WZWangmeng Zuo
Wangmeng Zuo
LLLiang Lin
Liang Lin
RYRuigang Yang
Ruigang Yang

1 November 2024
Verified
Book Chapter
Closed access
PDF file
HYHang Yao
Hang Yao
MLMing Liu
Ming Liu
ZYZhicun Yin
Zhicun Yin
ZYZifei Yan
Zifei Yan
XHXiaopeng Hong
Xiaopeng Hong
WZWangmeng Zuo
Wangmeng Zuo

7 March 2023 in Applied Intelligence
Verified
Journal Article
Closed access
PDF file
YLYu Li
Yu Li
MLMing Liu
Ming Liu
YYYaling Yi
Yaling Yi
QLQince Li
Qince Li
DRDongwei Ren
Dongwei Ren
WZWangmeng Zuo
Wangmeng Zuo

27 November 2024
Verified
Book Chapter
Closed access
PDF file
XLXiaoyu Liu
Xiaoyu Liu
YWYuxiang Wei
Yuxiang Wei
MLMing Liu
Ming Liu
XLXianhui Lin
Xianhui Lin
PRPeiran Ren
Peiran Ren
WZWangmeng Zuo
Wangmeng Zuo

13 December 2023 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
HWHaolin Wang
Haolin Wang
AAA A
A A
MLMing Liu
Ming Liu
XWXiaohe Wu
Xiaohe Wu
WZWangmeng Zuo
Wangmeng Zuo
Image retouching, aiming to regenerate the visually pleasing renditions of given images, is a subjective task where the users are with different aesthetic sensations. Most existing methods adopt a deterministic model to learn the retouching style from a specific expert, making it less flexible to meet diverse subjective preferences. Besides, the intrinsic diversity of an expert due to the targeted processing of different images is also deficiently described. To circumvent such issues, we propose to learn diverse image retouching with normalizing flow-based architectures. Unlike current flow-based methods which directly generate the output image, we argue that learning in a one-dimensional style space could 1) disentangle the retouching styles from the image content, 2) lead to a stable style presentation form, and 3) avoid the spatial disharmony effects. For obtaining meaningful image tone style representations, a joint-training pipeline is delicately designed, which is composed of a style encoder, a conditional RetouchNet, and the image tone style normalizing flow (TSFlow) module. In particular, the style encoder predicts the target style representation of an input image, which serves as the conditional information in the RetouchNet for retouching, while the TSFlow maps the style representation vector into a Gaussian distribution in the forward pass. After training, the TSFlow can generate diverse image tone style vectors by sampling from the Gaussian distribution. Extensive experiments on MIT-Adobe FiveK and PPR10K datasets show that our proposed method performs favorably against state-of-the-art methods and is effective in generating diverse results to satisfy different human aesthetic preferences. Source codeterministic and pre-trained models are publicly available at https://github.com/SSRHeart/TSFlow .