DiffGAR: Model-Agnostic Restoration from Generative Artifacts Using Image-to-Image Diffusion Models | |
Yin Yueqin2,3; Huang Lianghua1; Liu Yu1; Huang Kaiqi2,3 | |
2023-03-30 | |
会议日期 | 2022-12 |
会议地点 | Beijing, China |
关键词 | datasets generative modeling image generation image restoration |
英文摘要 | Recent generative models show impressive results in photo-realistic image generation. However, artifacts often inevitably appear in the generated results, leading to downgraded user experience and reduced performance in downstream tasks. This work aims to develop a plugin post-processing module for diverse generative models, which can faithfully restore images from diverse generative artifacts. This is challenging because: (1) Unlike traditional degradation patterns, generative artifacts are non-linear and the transformation function is highly complex. (2) There are no readily available artifact-image pairs. (3) Different from model-specific anti-artifact methods, a model-agnostic framework views the generator as a black-box machine and has no access to the architecture details. In this work, we first design a group of mechanisms to simulate generative artifacts of popular generators (i.e., GANs, autoregressive models, and diffusion models), given real images. Second, we implement the model-agnostic anti-artifact framework as an image-to-image diffusion model, due to its advantage in generation quality and capacity. Finally, we design a conditioning scheme for the diffusion model to enable both blind and non-blind image restoration. A guidance parameter is also introduced to allow for a trade-off between restoration accuracy and image quality. Extensive experiments show that our method significantly outperforms previous approaches on the proposed datasets and real-world artifact images. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/52139] |
专题 | 智能系统与工程 |
通讯作者 | Yin Yueqin |
作者单位 | 1.Machine Intelligence Technology Lab, Alibaba Group 2.Institute of Automation, Chinese Academy of Sciences 3.School of Artificial Intelligence, University of Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Yin Yueqin,Huang Lianghua,Liu Yu,et al. DiffGAR: Model-Agnostic Restoration from Generative Artifacts Using Image-to-Image Diffusion Models[C]. 见:. Beijing, China. 2022-12. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论