Biography :

Li Chenghua is an associate professor of the Institute of Automation, Chinese Academy of Sciences. He is graduated from the Institute of Automation of the Chinese Academy of Sciences with a doctor's degree in 2018, and has worked in the Institute since then. At present, He mainly engage in research in deep learning, image and video content enhancement and analysis. In the field of image and video enhancement, he has won more than 10 international famous competitions, including NTIRE and AIM, and have published more than 10 academic papers and applied for more than 20 invention patents. He is currently a member of the China Image and Graphics Society and a member of the CSIG Visual Big Data Special Committee. He has been awarded the title of Excellent Member of the 15th Batch of Science and Technology Town Leaders in Nanjing Province.

Publications :

• 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 Third Place.
• 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）Runner up of two tracks.
• 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  Track Champion.
• 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 and  Track 2: smartphone GPU Champion.
• 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 Track Champion.
• 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 Third Place、Track 2: Burst Runner up；NTIRE 2020 Challenge on Real Image Denoising: Track 2 sRGB Runner up.
• Chunjie Zhang, Chenghua Li, Jian Cheng. Few-Shot Visual Classification Using Image Pairs With Binary Transformation. TCSVT, 30(9):2867 - 2871, 2020.

Awards :

AIM 2020 Challenge on Rendering Realistic Bokeh Track1: CPU,Track 2: Smartphone GPU Winner；
AIM 2020 Challenge on Learned ISP Track 1: Fidelity Winner；
AIM 2020 Challenge on Scene Relighting and Illumination Estimation: Track 2 Illumination Settings Estimation Winner；
AIM 2022 Challenge on Reversed ISP（Track 1 S7，Track 2 P20）Runner-up;
AIM 2022 Challenge on Instagram Filter RemovalRunner-up;
AIM 2022 Challenge on Super-Resolution of Compressed Image 3rd-Place;
AIM 2020 Challenge on Efficient Super-Resolution Runner-up；
NTIRE 2020 Challenge on Real Image Denoising: Track 2 sRGB Runner-up；
NTIRE 2020 Challenge on Real Image Demoireing Track 1: Single Image 3rd-Place、Track 2: Burst Runner-up；
AIM 2019 Challenge on Constrained Super-Resolution Track 1: Parameters Runner-up,Track2: Inference 3rd-Place.