Výsledky vyhledávání - "Cai, Chunlei"

Report

F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration

Autor: Liu, Lu, Duan, Huiyu, Hu, Qiang, Yang, Liu, Cai, Chunlei, Ye, Tianxiao, Liu, Huayu, Zhang, Xiaoyun, Zhai, Guangtao

Artificial intelligence generative models exhibit remarkable capabilities in content creation, particularly in face image generation, customization, and restoration. However, current AI-generated faces (AIGFs) often fall short of human preferences du

Externí odkaz: http://arxiv.org/abs/2412.13155

Zobrazit plný text záznamu

Report

Rate-Perception Optimized Preprocessing for Video Coding

Autor: Ma, Chengqian, Wu, Zhiqiang, Cai, Chunlei, Zhang, Pengwei, Wang, Yi, Zheng, Long, Chen, Chao, Zhou, Quan

In the past decades, lots of progress have been done in the video compression field including traditional video codec and learning-based video codec. However, few studies focus on using preprocessing techniques to improve the rate-distortion performa

Externí odkaz: http://arxiv.org/abs/2301.10455

Zobrazit plný text záznamu

Report

Quality-Constant Per-Shot Encoding by Two-Pass Learning-based Rate Factor Prediction

Autor: Cai, Chunlei, Wang, Yi, Li, Xiaobo, Ye, Tianxiao

Providing quality-constant streams can simultaneously guarantee user experience and prevent wasting bit-rate. In this paper, we propose a novel deep learning based two-pass encoder parameter prediction framework to decide rate factor (RF), with which

Externí odkaz: http://arxiv.org/abs/2208.10739

Zobrazit plný text záznamu

Report

Content Adaptive and Error Propagation Aware Deep Video Compression

Autor: Lu, Guo, Cai, Chunlei, Zhang, Xiaoyun, Chen, Li, Ouyang, Wanli, Xu, Dong, Gao, Zhiyong

Recently, learning based video compression methods attract increasing attention. However, the previous works suffer from error propagation due to the accumulation of reconstructed error in inter predictive coding. Meanwhile, the previous learning bas

Externí odkaz: http://arxiv.org/abs/2003.11282

Zobrazit plný text záznamu

Report

DVC: An End-to-end Deep Video Compression Framework

Autor: Lu, Guo, Ouyang, Wanli, Xu, Dong, Zhang, Xiaoyun, Cai, Chunlei, Gao, Zhiyong

Conventional video compression approaches use the predictive coding architecture and encode the corresponding motion information and residual information. In this paper, taking advantage of both classical architecture in the conventional video compre

Externí odkaz: http://arxiv.org/abs/1812.00101

Zobrazit plný text záznamu