Zobrazeno 1 - 10
of 185
pro vyhledávání: '"Deforges, Olivier"'
Autor:
Blard, Théophile, Ladune, Théo, Philippe, Pierrick, Clare, Gordon, Jiang, Xiaoran, Déforges, Olivier
Overfitted image codecs offer compelling compression performance and low decoder complexity, through the overfitting of a lightweight decoder for each image. Such codecs include Cool-chic, which presents image coding performance on par with VVC while
Externí odkaz:
http://arxiv.org/abs/2403.11651
We propose a lightweight learned video codec with 900 multiplications per decoded pixel and 800 parameters overall. To the best of our knowledge, this is one of the neural video codecs with the lowest decoding complexity. It is built upon the overfit
Externí odkaz:
http://arxiv.org/abs/2402.03179
The high efficiency video coding (HEVC) standard and the joint exploration model (JEM) codec incorporate 35 and 67 intra prediction modes (IPMs) respectively, which are essential for efficient compression of Intra coded blocks. These IPMs are transmi
Externí odkaz:
http://arxiv.org/abs/2310.05623
Autor:
Liu, Xiaohong, Min, Xiongkuo, Sun, Wei, Zhang, Yulun, Zhang, Kai, Timofte, Radu, Zhai, Guangtao, Gao, Yixuan, Cao, Yuqin, Kou, Tengchuan, Dong, Yunlong, Jia, Ziheng, Li, Yilin, Wu, Wei, Hu, Shuming, Deng, Sibin, Xiao, Pengxiang, Chen, Ying, Li, Kai, Zhao, Kai, Yuan, Kun, Sun, Ming, Cong, Heng, Wang, Hao, Fu, Lingzhi, Zhang, Yusheng, Zhang, Rongyu, Shi, Hang, Xu, Qihang, Xiao, Longan, Ma, Zhiliang, Agarla, Mirko, Celona, Luigi, Rota, Claudio, Schettini, Raimondo, Huang, Zhiwei, Li, Yanan, Wang, Xiaotao, Lei, Lei, Liu, Hongye, Hong, Wei, Chuang, Ironhead, Lin, Allen, Guan, Drake, Chen, Iris, Lou, Kae, Huang, Willy, Tasi, Yachun, Kao, Yvonne, Fan, Haotian, Kong, Fangyuan, Zhou, Shiqi, Liu, Hao, Lai, Yu, Chen, Shanshan, Wang, Wenqi, Wu, Haoning, Chen, Chaofeng, Zhu, Chunzheng, Guo, Zekun, Zhao, Shiling, Yin, Haibing, Wang, Hongkui, Meftah, Hanene Brachemi, Fezza, Sid Ahmed, Hamidouche, Wassim, Déforges, Olivier, Shi, Tengfei, Mansouri, Azadeh, Motamednia, Hossein, Bakhtiari, Amir Hossein, Aznaveh, Ahmad Mahmoudi
This paper reports on the NTIRE 2023 Quality Assessment of Video Enhancement Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2023. This challenge is to address a major cha
Externí odkaz:
http://arxiv.org/abs/2307.09729
Federated learning (FL) has emerged to enable global model training over distributed clients' data while preserving its privacy. However, the global trained model is vulnerable to the evasion attacks especially, the adversarial examples (AEs), carefu
Externí odkaz:
http://arxiv.org/abs/2206.02131
Autor:
Bonnineau, Charles, Hamidouche, Wassim, Travers, Jean-François, Sidaty, Naty, Aubié, Jean-Yves, Deforges, Olivier
Publikováno v:
2021 International Conference on Visual Communications and Image Processing (VCIP)
In this paper, we present CAESR, an hybrid learning-based coding approach for spatial scalability based on the versatile video coding (VVC) standard. Our framework considers a low-resolution signal encoded with VVC intra-mode as a base-layer (BL), an
Externí odkaz:
http://arxiv.org/abs/2202.00416
Autor:
Bonnineau, Charles, Hamidouche, Wassim, Fournier, Jerome, Sidaty, Naty, Travers, Jean-Francois, Deforges, Olivier
With the growing data consumption of emerging video applications and users requirement for higher resolutions, up to 8K, a huge effort has been made in video compression technologies. Recently, versatile video coding (VVC) has been standardized by th
Externí odkaz:
http://arxiv.org/abs/2109.06555
Versatile Video Coding (VVC) is the next generation video coding standard finalized in July 2020. VVC introduces new coding tools enhancing the coding efficiency compared to its predecessor High Efficiency Video Coding (HEVC). These new tools have a
Externí odkaz:
http://arxiv.org/abs/2107.11659
The major part of the vanilla vision transformer (ViT) is the attention block that brings the power of mimicking the global context of the input image. For better performance, ViT needs large-scale training data. To overcome this data hunger limitati
Externí odkaz:
http://arxiv.org/abs/2106.03734
Salient human detection (SHD) in dynamic 360{\deg} immersive videos is of great importance for various applications such as robotics, inter-human and human-object interaction in augmented reality. However, 360{\deg} video SHD has been seldom discusse
Externí odkaz:
http://arxiv.org/abs/2105.11578