In this paper, we present a Neural Preset technique to address the limitations of existing color style transfer methods, including visual artifacts, vast memory requirement, and slow style switching speed. Our method is based on two core designs. First, we propose Deterministic Neural Color Mapping (DNCM) to consistently operate on each pixel via an image-adaptive color mapping matrix, avoiding artifacts and supporting high-resolution inputs with a small memory footprint. Second, we develop a two-stage pipeline by dividing the task into color normalization and stylization, which allows efficient style switching by extracting color styles as presets and reusing them on normalized input images. Due to the unavailability of pairwise datasets, we describe how to train Neural Preset via a self-supervised strategy. Various advantages of Neural Preset over existing methods are demonstrated through comprehensive evaluations. Notably, Neural Preset enables stable 4K color style transfer in real-time without artifacts. Besides, we show that our trained model can naturally support multiple applications without fine-tuning, including low-light image enhancement, underwater image correction, image dehazing, and image harmonization. Project page with demos: https://zhkkke.github.io/NeuralPreset .

翻译：本文提出一种神经预设技术，以解决现有色彩风格迁移方法存在的视觉伪影、内存需求大及风格切换速度慢等局限性。该方法基于两个核心设计：首先，提出确定性神经色彩映射（DNCM），通过图像自适应色彩映射矩阵对每个像素进行一致性处理，从而避免伪影，并以低内存占用支持高分辨率输入。其次，构建两阶段流水线，将任务分解为色彩归一化和风格化，通过将色彩风格提取为预设并复用于归一化输入图像，实现高效风格切换。针对成对数据集缺失的问题，本文描述了如何通过自监督策略训练神经预设。通过全面评估，验证了神经预设相较于现有方法的多种优势。值得注意的是，神经预设能实现无伪影的实时4K色彩风格迁移。此外，实验表明，训练后的模型无需微调即可自然支持多项应用，包括低光照图像增强、水下图像校正、图像去雾及图像协调。项目页面及演示：https://zhkkke.github.io/NeuralPreset。