1 code implementation • 21 Jun 2023 • Xiangjun Tang, Linjun Wu, He Wang, Bo Hu, Xu Gong, Yuchen Liao, Songnan Li, Qilong Kou, Xiaogang Jin
Styled online in-between motion generation has important application scenarios in computer animation and games.
no code implementations • 8 Jul 2022 • Zhengang Li, Sheng Lin, Shan Liu, Songnan Li, Xue Lin, Wei Wang, Wei Jiang
Recently, high-quality video conferencing with fewer transmission bits has become a very hot and challenging problem.
no code implementations • 16 Nov 2021 • Wei Jiang, Wei Wang, Songnan Li, Shan Liu
This work addresses two major issues of end-to-end learned image compression (LIC) based on deep neural networks: variable-rate learning where separate networks are required to generate compressed images with varying qualities, and the train-test mismatch between differentiable approximate quantization and true hard quantization.
no code implementations • 15 Jun 2021 • Sheng Lin, Wei Jiang, Wei Wang, Kaidi Xu, Yanzhi Wang, Shan Liu, Songnan Li
Compressing Deep Neural Network (DNN) models to alleviate the storage and computation requirements is essential for practical applications, especially for resource limited devices.
1 code implementation • 16 Apr 2019 • Di Zhao, Lan Ma, Songnan Li, Dahai Yu
When taking photos in dim-light environments, due to the small amount of light entering, the shot images are usually extremely dark, with a great deal of noise, and the color cannot reflect real-world color.
1 code implementation • CVPR 2019 • Fanzi Wu, Linchao Bao, Yajing Chen, Yonggen Ling, Yibing Song, Songnan Li, King Ngi Ngan, Wei Liu
The main ingredient of the view alignment loss is a differentiable dense optical flow estimator that can backpropagate the alignment errors between an input view and a synthetic rendering from another input view, which is projected to the target view through the 3D shape to be inferred.
no code implementations • ICLR 2020 • Jingwei Guan, Cheng Pan, Songnan Li, Dahai Yu
In this work, an end-to-end novel framework, including high-to-low network and low-to-high network, is proposed to solve the above problems with dual Generative Adversarial Networks (GAN).
Multimedia
no code implementations • 10 Dec 2017 • Fanzi Wu, Songnan Li, Tianhao Zhao, King Ngi Ngan, Lv Sheng
2D landmarks are detected and used to initialize the 3D shape and mapping matrices.