Content affinity loss including feature and pixel affinity is a main problem
which leads to artifacts in photorealistic and video style transfer. This paper
proposes a new framework named CAP-VSTNet, which consists of a new reversible
residual network and an unbiased linear transform module, for versatile style
transfer. This reversible residual network can not only preserve content
affinity but not introduce redundant information as traditional reversible
networks, and hence facilitate better stylization. Empowered by Matting
Laplacian training loss which can address the pixel affinity loss problem led
by the linear transform, the proposed framework is applicable and effective on
versatile style transfer. Extensive experiments show that CAP-VSTNet can
produce better qualitative and quantitative results in comparison with the
state-of-the-art methods.

本文提出了一种名为 CAP-VSTNet 的新框架，其中包括一个新的可逆残差网络和一个无偏线性变换模块，用于各种样式转换。通过 Matting Laplacian 训练损失，该框架可解决由线性变换引起的像素亲和力丢失问题，避免引入冗余信息并提高风格化效果。

CAP-VSTNet: 内容关联性保持的通用风格迁移

CAP-VSTNet: Content Affinity Preserved Versatile Style Transfer

Deep residual networks (ResNets) have significantly pushed forward the
state-of-the-art on image classification, increasing in performance as networks
grow both deeper and wider. However, memory consumption becomes a bottleneck,
as one needs to store the activations in order to calculate gradients using
backpropagation. We present the Reversible Residual Network (RevNet), a variant
of ResNets where each layer's activations can be reconstructed exactly from the
next layer's. Therefore, the activations for most layers need not be stored in
memory during backpropagation. We demonstrate the effectiveness of RevNets on
CIFAR-10, CIFAR-100, and ImageNet, establishing nearly identical classification
accuracy to equally-sized ResNets, even though the activation storage
requirements are independent of depth.

该研究介绍了一种新型的具有可逆性的深度残差网络，名为 RevNet，能够通过其后续层的激活来精确地重建每一层的激活，从而克服了传统深度残差网络在反向传播过程中所需要大量的存储空间，实现了与相同大小的深度残余网络相似的图像分类准确率。