arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.14373cs.CV
收藏

D2C-SR:一种从发散到收敛的真实世界图像超分辨率方法

D2C-SR: A Divergence to Convergence Approach for Real-World Image Super-Resolution

Megvii Technology(旷视科技);Kuaishou Technology(快手科技);Great Wall Motor Company Limited(长城汽车股份有限公司);University of Electronic Science and Technology of China(电子科技大学)

Youwei Li, Haibin Huang, Lanpeng Jia, Haoqiang Fan, Shuaicheng Liu

摘要:

在本文中,我们提出了D2C-SR,一个新的框架,现实世界的图像超分辨率的任务。作为一个不适定问题,超分辨率相关任务的关键挑战是对于给定的低分辨率输入可以有多个预测。大多数经典的基于深度学习的方法忽略了基本事实,并且缺乏对底层高频分布的明确建模,这导致模糊的结果。近年来,一些基于GAN的方法或学习超分辨率空间的方法可以生成模拟纹理,但不能保证纹理的准确性,其定量性能较低。重新思考两者,我们以离散形式学习底层高频细节的分布,并提出了一个两阶段的管道:发散阶段到收敛阶段。在发散阶段,我们提出了一个基于树结构的深度网络作为我们的发散骨干。发散损失被提出来鼓励从基于树的网络生成的结果发散到可能的高频表示中,这是我们对底层高频分布进行离散建模的方式。在收敛阶段,我们分配空间权重来融合这些不同的预测,以获得具有更准确细节的最终输出。我们的方法提供了一个方便的端到端的推理方式。我们对几个真实世界的基准进行了评估,包括一个新提出的具有x8缩放因子的D2CREalSR数据集。我们的实验表明,D2C-SR实现了更好的准确性和视觉上的改进,与国家的最先进的方法,与一个显着较少的参数数量和我们的D2C结构也可以作为一个广义的结构,一些其他的方法,以获得改善。我们的代码和数据集可在https://github.com/megvii-research/D2C-SR上获得

英文摘要:

In this paper, we present D2C-SR, a novel framework for the task of real-world image super-resolution. As an ill-posed problem, the key challenge in super-resolution related tasks is there can be multiple predictions for a given low-resolution input. Most classical deep learning based approaches ignored the fundamental fact and lack explicit modeling of the underlying high-frequency distribution which leads to blurred results. Recently, some methods of GAN-based or learning super-resolution space can generate simulated textures but do not promise the accuracy of the textures which have low quantitative performance. Rethinking both, we learn the distribution of underlying high-frequency details in a discrete form and propose a two-stage pipeline: divergence stage to convergence stage. At divergence stage, we propose a tree-based structure deep network as our divergence backbone. Divergence loss is proposed to encourage the generated results from the tree-based network to diverge into possible high-frequency representations, which is our way of discretely modeling the underlying high-frequency distribution. At convergence stage, we assign spatial weights to fuse these divergent predictions to obtain the final output with more accurate details. Our approach provides a convenient end-to-end manner to inference. We conduct evaluations on several real-world benchmarks, including a new proposed D2CRealSR dataset with x8 scaling factor. Our experiments demonstrate that D2C-SR achieves better accuracy and visual improvements against state-of-the-art methods, with a significantly less parameters number and our D2C structure can also be applied as a generalized structure to some other methods to obtain improvement. Our codes and dataset are available at https://github.com/megvii-research/D2C-SR

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑