Zobrazeno 1 - 10
of 32
pro vyhledávání: '"He, Dailan"'
Autor:
Ge, Xingtong, Luo, Jixiang, Zhang, Xinjie, Xu, Tongda, Lu, Guo, He, Dailan, Geng, Jing, Wang, Yan, Zhang, Jun, Qin, Hongwei
Prior research on deep video compression (DVC) for machine tasks typically necessitates training a unique codec for each specific task, mandating a dedicated decoder per task. In contrast, traditional video codecs employ a flexible encoder controller
Externí odkaz:
http://arxiv.org/abs/2404.04848
Autor:
Zhang, Xinjie, Ge, Xingtong, Xu, Tongda, He, Dailan, Wang, Yan, Qin, Hongwei, Lu, Guo, Geng, Jing, Zhang, Jun
Implicit neural representations (INRs) recently achieved great success in image representation and compression, offering high visual quality and fast rendering speeds with 10-1000 FPS, assuming sufficient GPU resources are available. However, this re
Externí odkaz:
http://arxiv.org/abs/2403.08551
Autor:
Zhang, Xinjie, Gao, Shenyuan, Liu, Zhening, Shao, Jiawei, Ge, Xingtong, He, Dailan, Xu, Tongda, Wang, Yan, Zhang, Jun
Existing learning-based stereo image codec adopt sophisticated transformation with simple entropy models derived from single image codecs to encode latent representations. However, those entropy models struggle to effectively capture the spatial-disp
Externí odkaz:
http://arxiv.org/abs/2403.08505
Autor:
Zhang, Xinjie, Yang, Ren, He, Dailan, Ge, Xingtong, Xu, Tongda, Wang, Yan, Qin, Hongwei, Zhang, Jun
Implicit neural representations (INRs) have emerged as a promising approach for video storage and processing, showing remarkable versatility across various video tasks. However, existing methods often fail to fully leverage their representation capab
Externí odkaz:
http://arxiv.org/abs/2402.18152
Autor:
Xu, Tongda, Zhu, Ziran, Li, Jian, He, Dailan, Wang, Yuanyuan, Sun, Ming, Li, Ling, Qin, Hongwei, Wang, Yan, Liu, Jingjing, Zhang, Ya-Qin
Diffusion Inverse Solvers (DIS) are designed to sample from the conditional distribution $p_{\theta}(X_0|y)$, with a predefined diffusion model $p_{\theta}(X_0)$, an operator $f(\cdot)$, and a measurement $y=f(x'_0)$ derived from an unknown image $x'
Externí odkaz:
http://arxiv.org/abs/2403.12063
Autor:
Guo, Lina, Wang, Yuanyuan, Xu, Tongda, Luo, Jixiang, He, Dailan, Ji, Zhenjun, Wang, Shanshan, Wang, Yang, Qin, Hongwei
JPEG is one of the most popular image compression methods. It is beneficial to compress those existing JPEG files without introducing additional distortion. In this paper, we propose a deep learning based method to further compress JPEG images lossle
Externí odkaz:
http://arxiv.org/abs/2308.13287
Autor:
Xu, Tongda, Zhang, Qian, Li, Yanghao, He, Dailan, Wang, Zhe, Wang, Yuanyuan, Qin, Hongwei, Wang, Yan, Liu, Jingjing, Zhang, Ya-Qin
We propose conditional perceptual quality, an extension of the perceptual quality defined in \citet{blau2018perception}, by conditioning it on user defined information. Specifically, we extend the original perceptual quality $d(p_{X},p_{\hat{X}})$ to
Externí odkaz:
http://arxiv.org/abs/2308.08154
Autor:
Zhang, Yi, Li, Dasong, Shi, Xiaoyu, He, Dailan, Song, Kangning, Wang, Xiaogang, Qin, Hongwei, Li, Hongsheng
How to aggregate spatial information plays an essential role in learning-based image restoration. Most existing CNN-based networks adopt static convolutional kernels to encode spatial information, which cannot aggregate spatial information adaptively
Externí odkaz:
http://arxiv.org/abs/2303.02881
This paper considers the problem of lossy neural image compression (NIC). Current state-of-the-art (sota) methods adopt uniform posterior to approximate quantization noise, and single-sample pathwise estimator to approximate the gradient of evidence
Externí odkaz:
http://arxiv.org/abs/2209.13834
Autor:
Xu, Tongda, Gao, Han, Gao, Chenjian, Wang, Yuanyuan, He, Dailan, Pi, Jinyong, Luo, Jixiang, Zhu, Ziyu, Ye, Mao, Qin, Hongwei, Wang, Yan, Liu, Jingjing, Zhang, Ya-Qin
In this paper, we consider the problem of bit allocation in Neural Video Compression (NVC). First, we reveal a fundamental relationship between bit allocation in NVC and Semi-Amortized Variational Inference (SAVI). Specifically, we show that SAVI wit
Externí odkaz:
http://arxiv.org/abs/2209.09422