AdaCM: Adaptive ColorMLP for Real-Time Universal Photo-realistic Style Transfer
This addresses the need for efficient, high-quality style transfer for applications like image editing, though it is incremental over existing methods.
The paper tackled the problem of achieving real-time photo-realistic style transfer without artifacts by proposing AdaCM, which uses a CNN to adaptively predict parameters for a small ColorMLP, resulting in processing a 4K image in 6ms on a V100 GPU.
Photo-realistic style transfer aims at migrating the artistic style from an exemplar style image to a content image, producing a result image without spatial distortions or unrealistic artifacts. Impressive results have been achieved by recent deep models. However, deep neural network based methods are too expensive to run in real-time. Meanwhile, bilateral grid based methods are much faster but still contain artifacts like overexposure. In this work, we propose the \textbf{Adaptive ColorMLP (AdaCM)}, an effective and efficient framework for universal photo-realistic style transfer. First, we find the complex non-linear color mapping between input and target domain can be efficiently modeled by a small multi-layer perceptron (ColorMLP) model. Then, in \textbf{AdaCM}, we adopt a CNN encoder to adaptively predict all parameters for the ColorMLP conditioned on each input content and style image pair. Experimental results demonstrate that AdaCM can generate vivid and high-quality stylization results. Meanwhile, our AdaCM is ultrafast and can process a 4K resolution image in 6ms on one V100 GPU.