Dingquan Li

I am a Postdoc at Peng Cheng Laboratory (PCL), where I am advised by Prof. Ge Li. I did my PhD at School of Mathematical Sciences, BICMR at Peking University, where I was advised by Prof. Ming Jiang and Prof. Tingting Jiang. During this period, I was also a research assistant in the VIE group at NELVT of Peking University. Before coming to Peking University in 2015, I did my bachelors at Nankai University.

Email  /  CV;CV_cn  /  Google Scholar  /  Github  /  ResearchGate  /  Linkedin

My main interest lies in image, video, and point cloud processing, including:

• Point Cloud Quality Assessment
• Image/Video Quality Assessment
• Perceptual Optimization

A mixed datasets training strategy for training a single unified VQA model with multiple datasets

Most conventional objective metrics prefer blurry animals (relatively complex visual content) over clear the blue sky (simple content), contradicting with human perception: content-aware features help ...

Normalization-embedded loss is conducive to the faster convergence and better performance of the IQA model.

Content dependency and temporal-memory effects of HVS are considered in the design of NR-VQA models.

High-level semantic features extracted from pre-trained image classification models help NR-IQA.

Template credit to Jon Barron