paper-with-me

홈 › Papers

DVC-P: Deep Video Compression with Perceptual Optimizations

2021-09-22 · Saiping Zhang, Marta Mrak, Luis Herranz, Marc Górriz, Shuai Wan, Fuzheng Yang

Recent years have witnessed the significant development of learning-based video compression methods, which aim at optimizing objective or perceptual quality and bit rates. In this paper, we introduce deep video compression with perceptual optimizations (DVC-P), which aims at increasing perceptual quality of decoded videos. Our proposed DVC-P is based on Deep Video Compression (DVC) network, but improves it with perceptual optimizations. Specifically, a discriminator network and a mixed loss are employed to help our network trade off among distortion, perception and rate. Furthermore, nearest-neighbor interpolation is used to eliminate checkerboard artifacts which can appear in sequences encoded with DVC frameworks. Thanks to these two improvements, the perceptual quality of decoded sequences is improved. Experimental results demonstrate that, compared with the baseline DVC, our proposed method can generate videos with higher perceptual quality achieving 12.27% reduction in a perceptual BD-rate equivalent, on average.

📄 PDF Abstract BibTeX arXiv:2109.10849

Code (1)

SaipingZhang/DVC_P tf

Tasks

Video Compression

Similar Papers 제목 키워드 기반

Generative Latent Video Compression

2025-10-11 · Zongyu Guo, Zhaoyang Jia, Jiahao Li, Xiaoyi Zhang 외 arxiv

Perceptual optimization is widely recognized as essential for neural compression, yet balancing the rate-distortion-perception tradeoff remains challenging. This difficulty is especially pronounced in video compression, …

Controllable Generative Video Compression

2026-04-08 · Ding Ding, Daowen Li, Ying Chen, Yixin Gao 외 arxiv

Perceptual video compression adopts generative video modeling to improve perceptual realism but frequently sacrifices signal fidelity, diverging from the goal of video compression to faithfully reproduce visual signal. T…

Video Generation

Perceptual Learned Video Compression with Recurrent Conditional GAN

2021-09-07 · Ren Yang, Radu Timofte, Luc van Gool

This paper proposes a Perceptual Learned Video Compression (PLVC) approach with recurrent conditional GAN. We employ the recurrent auto-encoder-based compression network as the generator, and most importantly, we propose…

Video Compression

High Visual-Fidelity Learned Video Compression

2023-10-07 · Meng Li, Yibo Shi, Jing Wang, Yunqi Huang

With the growing demand for video applications, many advanced learned video compression methods have been developed, outperforming traditional methods in terms of objective quality metrics such as PSNR. Existing methods …

Video Compression

Generative Neural Video Compression via Video Diffusion Prior

2025-12-04 · Qi Mao, Hao Cheng, Tinghan Yang, Libiao Jin 외 arxiv

We present GNVC-VD, the first DiT-based generative neural video compression framework built upon an advanced video generation foundation model, where spatio-temporal latent compression and sequence-level generative refin…

Video Generation