AdaCM: Adaptive ColorMLP for Real-Time Universal Photo-realistic Style Transfer

TL;DR

AdaCM introduces an adaptive, neural network-based framework for real-time, high-quality photo-realistic style transfer that is both efficient and capable of processing high-resolution images rapidly.

Contribution

The paper proposes AdaCM, a novel adaptive framework combining a CNN encoder and a small MLP for fast, universal photo-realistic style transfer with high quality.

Findings

Achieves high-quality stylization with vivid results.

Processes 4K images in just 6ms on a V100 GPU.

Outperforms existing methods in speed and quality.

Abstract

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.