paper-with-me

홈 › Papers

High-dimensional Assisted Generative Model for Color Image Restoration

2021-08-14 · Kai Hong, CHUNHUA WU, Cailian Yang, Minghui Zhang, Yancheng Lu, Yuhao Wang, Qiegen Liu

This work presents an unsupervised deep learning scheme that exploiting high-dimensional assisted score-based generative model for color image restoration tasks. Considering that the sample number and internal dimension in score-based generative model have key influence on estimating the gradients of data distribution, two different high-dimensional ways are proposed: The channel-copy transformation increases the sample number and the pixel-scale transformation decreases feasible space dimension. Subsequently, a set of high-dimensional tensors represented by these transformations are used to train the network through denoising score matching. Then, sampling is performed by annealing Langevin dynamics and alternative data-consistency update. Furthermore, to alleviate the difficulty of learning high-dimensional representation, a progressive strategy is proposed to leverage the performance. The proposed unsupervised learning and iterative restoration algo-rithm, which involves a pre-trained generative network to obtain prior, has transparent and clear interpretation compared to other data-driven approaches. Experimental results on demosaicking and inpainting conveyed the remarkable performance and diversity of our proposed method.

📄 PDF Abstract BibTeX arXiv:2108.06460

Code (1)

yqx7150/hgm 공식 구현 pytorch

Tasks

DemosaickingDenoisingDiversityImage RestorationVocal Bursts Intensity Prediction

Methods 이 논문이 사용한 방법론

Inpainting Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.

Similar Papers 제목 키워드 기반

Generative Modeling in Structural-Hankel Domain for Color Image Inpainting

2022-11-25 · Zihao Li, CHUNHUA WU, Shenglin Wu, Wenbo Wan 외

In recent years, some researchers focused on using a single image to obtain a large number of samples through multi-scale features. This study intends to a brand-new idea that requires only ten or even fewer samples to c…

DiversityImage Inpainting

CAR-LOAM: Color-Assisted Robust LiDAR Odometry and Mapping

2025-02-24 · Yufei Lu, Yuetao Li, Zhizhou Jia, Qun Hao 외

In this letter, we propose a color-assisted robust framework for accurate LiDAR odometry and mapping (LOAM). Simultaneously receiving data from both the LiDAR and the camera, the framework utilizes the color information …

Wavelet Transform-assisted Adaptive Generative Modeling for Colorization

2021-07-09 · Jin Li, Wanyun Li, Zichen Xu, Yuhao Wang 외

Unsupervised deep learning has recently demonstrated the promise of producing high-quality samples. While it has tremendous potential to promote the image colorization task, the performance is limited owing to the high-d…

ColorizationDenoisingDiversityImage Colorization

VCGAN: Video Colorization with Hybrid Generative Adversarial Network

2021-04-26 · Yuzhi Zhao, Lai-Man Po, Wing-Yin Yu, Yasar Abbas Ur Rehman 외

We propose a hybrid recurrent Video Colorization with Hybrid Generative Adversarial Network (VCGAN), an improved approach to video colorization using end-to-end learning. The VCGAN addresses two prevalent issues in the v…

ColorizationGenerative Adversarial NetworkImage Colorization

Joint Intensity-Gradient Guided Generative Modeling for Colorization

2020-12-28 · Kai Hong, Jin Li, Wanyun Li, Cailian Yang 외

This paper proposes an iterative generative model for solving the automatic colorization problem. Although previous researches have shown the capability to generate plausible color, the edge color overflow and the requir…

Colorization