Graphics Interchange Format (GIF) is a highly portable graphics format that
is ubiquitous on the Internet. Despite their small sizes, GIF images often
contain undesirable visual artifacts such as flat color regions, false
contours, color shift, and dotted patterns. In this paper, we propose
GIF2Video, the first learning-based method for enhancing the visual quality of
GIFs in the wild. We focus on the challenging task of GIF restoration by
recovering information lost in the three steps of GIF creation: frame sampling,
color quantization, and color dithering. We first propose a novel CNN
architecture for color dequantization. It is built upon a compositional
architecture for multi-step color correction, with a comprehensive loss
function designed to handle large quantization errors. We then adapt the
SuperSlomo network for temporal interpolation of GIF frames. We introduce two
large datasets, namely GIF-Faces and GIF-Moments, for both training and
evaluation. Experimental results show that our method can significantly improve
the visual quality of GIFs, and outperforms direct baseline and
state-of-the-art approaches.

本文提出了 GIF2Video 方法，这是第一个应用于 GIF 图像增强的基于学习的方法，利用 CNN 网络实现了颜色去量化和时间插值等方面的帧重建与修复，实验结果表明，该方法优于现有基线方法和先进技术，可以显著改善 GIF 动画的视觉质量。

GIF2Video：GIF 图像的颜色去量化和时间插值

GIF2Video: Color Dequantization and Temporal Interpolation of GIF images

The Super-Resolution Generative Adversarial Network (SRGAN) is a seminal work
that is capable of generating realistic textures during single image
super-resolution. However, the hallucinated details are often accompanied with
unpleasant artifacts. To further enhance the visual quality, we thoroughly
study three key components of SRGAN - network architecture, adversarial loss
and perceptual loss, and improve each of them to derive an Enhanced SRGAN
(ESRGAN). In particular, we introduce the Residual-in-Residual Dense Block
(RRDB) without batch normalization as the basic network building unit.
Moreover, we borrow the idea from relativistic GAN to let the discriminator
predict relative realness instead of the absolute value. Finally, we improve
the perceptual loss by using the features before activation, which could
provide stronger supervision for brightness consistency and texture recovery.
Benefiting from these improvements, the proposed ESRGAN achieves consistently
better visual quality with more realistic and natural textures than SRGAN and
won the first place in the PIRM2018-SR Challenge. The code is available at
this https URL .

该研究通过提出 ESRGAN，改进了 SRGAN 的网络架构、对抗损失和感知损失三个关键部分。ESRGAN 获得了 PIRM2018-SR 挑战的第一名，并取得了比 SRGAN 更好的视觉质量和更真实、更自然的纹理。