Zobrazeno 1 - 10
of 2 867
pro vyhledávání: '"Wen Hsiao"'
Linear block transform coding remains a fundamental component of image and video compression. Although the Discrete Cosine Transform (DCT) is widely employed in all current compression standards, its sub-optimality has sparked ongoing research into d
Externí odkaz:
http://arxiv.org/abs/2411.18494
Most learned B-frame codecs with hierarchical temporal prediction suffer from the domain shift issue caused by the discrepancy in the Group-of-Pictures (GOP) size used for training and test. As such, the motion estimation network may fail to predict
Externí odkaz:
http://arxiv.org/abs/2410.21763
In this paper, we first show that current learning-based video codecs, specifically the SSF codec, are not suitable for real-world applications due to the mismatch between the encoder and decoder caused by floating-point round-off errors. To address
Externí odkaz:
http://arxiv.org/abs/2410.20145
This paper aims to delve into the rate-distortion-complexity trade-offs of modern neural video coding. Recent years have witnessed much research effort being focused on exploring the full potential of neural video coding. Conditional autoencoders hav
Externí odkaz:
http://arxiv.org/abs/2410.03898
Autor:
Kao, Chia-Hao, Chien, Cheng, Tseng, Yu-Jen, Chen, Yi-Hsin, Gnutti, Alessandro, Lo, Shao-Yuan, Peng, Wen-Hsiao, Leonardi, Riccardo
This paper presents the first-ever study of adapting compressed image latents to suit the needs of downstream vision tasks that adopt Multimodal Large Language Models (MLLMs). MLLMs have extended the success of large language models to modalities (e.
Externí odkaz:
http://arxiv.org/abs/2407.19651
Autor:
Chen, Yi-Hsin, Ho, Kuan-Wei, Tsai, Shiau-Rung, Lin, Guan-Hsun, Gnutti, Alessandro, Peng, Wen-Hsiao, Leonardi, Riccardo
This work introduces a Transformer-based image compression system. It has the flexibility to switch between the standard image reconstruction and the denoising reconstruction from a single compressed bitstream. Instead of training separate decoders f
Externí odkaz:
http://arxiv.org/abs/2402.12888
Learned hierarchical B-frame coding aims to leverage bi-directional reference frames for better coding efficiency. However, the domain shift between training and test scenarios due to dataset limitations poses a challenge. This issue arises from trai
Externí odkaz:
http://arxiv.org/abs/2402.12816
Autor:
Gnutti, Alessandro, Della Fiore, Stefano, Savardi, Mattia, Chen, Yi-Hsin, Leonardi, Riccardo, Peng, Wen-Hsiao
The incorporation of LiDAR technology into some high-end smartphones has unlocked numerous possibilities across various applications, including photography, image restoration, augmented reality, and more. In this paper, we introduce a novel direction
Externí odkaz:
http://arxiv.org/abs/2401.06517
Autor:
Chen, Yi-Hsin, Xie, Hong-Sheng, Chen, Cheng-Wei, Gao, Zong-Lin, Benjak, Martin, Peng, Wen-Hsiao, Ostermann, Jörn
Conditional coding has lately emerged as the mainstream approach to learned video compression. However, a recent study shows that it may perform worse than residual coding when the information bottleneck arises. Conditional residual coding was thus p
Externí odkaz:
http://arxiv.org/abs/2312.15829
Publikováno v:
Computational and Structural Biotechnology Journal, Vol 24, Iss , Pp 690-698 (2024)
Precision health extends beyond the scope of precision medicine and involves a broader range of activities, including the prediction, prevention, treatment, and management of diseases. Tailored to specific populations, precision health offers persona
Externí odkaz:
https://doaj.org/article/3acc5c97d01c4d00864740a6ab5b7303
