个人简介 :

李成华，中国科学院自动化研究所副研究员，2018年在中国科学院自动化研究所博士毕业，并留所工作至今。目前主要从事图像与视频增强大模型研究，在图像视频增强领域获得国际著名竞赛NTIRE、AIM冠亚季军10余项，发表学术论文10余篇，申请发明专利20余项。现为中国图象图形学会会员、CSIG视觉大数据专委会委员，荣获南京市第十五批科技镇长团优秀团员。

发表论文 :

• Chenghua Li, Bo Yang, Zhiqi Wu, Gao Chen, and Yihan Yu. Shadow removal based on diffusion, segmentation and super-resolution models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2024.
• Xiaoran Qin, Yu Zhu, Chenghua Li*, Peisong Wang, Jian Cheng. CIDBNet: A Consecutively-Interactive Dual-Branch Network for JPEG Compressed Image Super-Resolution. ECCV 2022 Workshops, AIM 2022 Challenge on Super-Resolution on Compressed Image第三名.
• Xiaoyi Dong, Yu Zhu, Chenghua Li*, Peisong Wang, Jian Cheng. RISPNet: A Network for Reversed Image Signal Processing. ECCV 2022 Workshops, AIM 2022 Challenge on Reversed ISP（Track 1 S7，Track 2 P20）双赛道亚军.
• Yu Zhu, Bosong Ding, Chenghua Li*, Wanli Qian, Fangya Li, Yiheng Yao, Ruipeng Gang, Chunjie Zhang, Jian Cheng. LTNet: Light Transfer Network for Depth Guided Image Relighting. CVPR Workshops, 2021.
• Zhuolong Jiang, Chengzhi Shen, Chenghua Li*, Hongzhi Liu, Wei Chen. Noise Map Guided Inpainting Network for Low-Light Image Enhancement. PRCV, 2021:201-213. 
• Zhu Yu, Zhenyu Guo, Tian Liang, Xiangyu He, Chenghua Li*, Cong Leng, Bo Jiang, Yifan Zhang, Jian Cheng. EEDNet: Enhanced Encoder-Decoder Network for AutoISP. ECCV 2020 Workshops, AIM 2020 on Learned ISP Track1: Fidelity冠军.
• Qian Ming, Congyu Qiao, Jiamin Lin, Zhenyu Guo, Chenghua Li*, Cong Leng, Jian Cheng. BGGAN: Bokeh-Glass Generative Adversarial Network for Rendering Realistic Bokeh. ECCV 2020 Workshops, AIM 2020 on Rendering Realistic Bokeh Track1: CPU和Track 2: smartphone GPU双赛道冠军.
• Liping Dong, Yu Zhu, Zhuolong Jiang, Xiangyu He, Zhaohui Meng, Chenghua Li*, Cong Leng, Jian Cheng. An Ensemble Neural Network for Scene Relighting with Light Classification. ECCV 2020 Workshops, AIM 2020 on Scene Relighting and Illumination Estimation: Track 2 Illumination Settings Estimation冠军.
• Shuai Liu, Chenghua Li*, Nan Nan, Ziyao Zong, Ruixia Song. MMDM: Multi-frame and Multi-scale for Image Demoiréing. CVPR 2020 Workshops, NTIRE 2020 Challenge on Real Image Demoireing Track 1: Single Image季军、Track 2: Burst亚军；NTIRE 2020 Challenge on Real Image Denoising: Track 2 sRGB 亚军.
• Chunjie Zhang, Chenghua Li, Jian Cheng. Few-Shot Visual Classification Using Image Pairs With Binary Transformation. TCSVT, 30(9):2867 - 2871, 2020.

获奖情况 :

AIM 2020 Challenge on Rendering Realistic Bokeh Track1: CPU,Track 2: Smartphone GPU 双赛道冠军；

AIM 2020 Challenge on Learned ISP Track 1: Fidelity冠军；
AIM 2020 Challenge on Scene Relighting and Illumination Estimation: Track 2 Illumination Settings Estimation冠军；
AIM 2022 Challenge on Reversed ISP（Track 1 S7，Track 2 P20）双赛道亚军;
AIM 2022 Challenge on Instagram Filter Removal亚军;
AIM 2022 Challenge on Super-Resolution of Compressed Image季军;
AIM 2020 Challenge on Efficient Super-Resolution 亚军；
NTIRE 2020 Challenge on Real Image Denoising: Track 2 sRGB 亚军；
NTIRE 2020 Challenge on Real Image Demoireing Track 1: Single Image季军、Track 2: Burst亚军；
AIM 2019 Challenge on Constrained Super-Resolution Track 1: Parameters亚军及Track2: Inference季军。