基于可学习贝塞尔流的非线性颜色迁移
Nonlinear Color Transfer via Learnable Bezier Flows
用贝塞尔曲线参数化替代流模型中的线性传输路径，可缓解颜色迁移中的轨迹错位与伪影；该非线性路径参数化思路可迁移到其他基于流的图像到图像翻译与风格化任务。
原文依据 replaces linear paths with Bezier trajectories, enabling smooth, nonlinear, and perceptually coherent color transfer
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论颜色迁移旨在将内容图像（源）的颜色分布匹配到风格图像（目标）的颜色分布，同时保持结构与感知真实感。然而，ModFlows 等基于调制的流模型由于依赖严格的线性传输路径，常常产生轨迹错位与伪影。我们提出 NCT，一种非线性颜色迁移框架，用贝塞尔轨迹替代线性路径，从而实现平滑、非线性且感知连贯的颜色迁移。这种参数化使传输过程能够向合理的中间颜色区域弯曲，改善内容与风格的对齐并减少色度失真。我们进一步在编码器中引入混合专家（MoE）模块，为不同的色度区域选择轨迹专家，提升对具有复杂光照与材质的异构数据的泛化能力。实验表明，NCT 减少了伪影，并比先前的基于流的方法实现了更稳定的颜色迁移，在 3D 渲染或高度纹理化的图像上尤为明显。代码见补充材料。
英文原文摘要 1095 字符
Color transfer aims to match the color distribution of a content image (source) to that of a style image (target) while preserving structure and perceptual realism. Yet modulation-based flow models such as ModFlows often produce trajectory misalignment and artifacts because they rely on strictly linear transport paths. We propose NCT, a nonlinear color transfer framework that replaces linear paths with Bezier trajectories, enabling smooth, nonlinear, and perceptually coherent color transfer. This parameterization lets the transport bend toward plausible intermediate color regimes, improving content-style alignment and reducing chromatic distortion. We further incorporate a Mixture of Experts (MoE) module in the encoder to select trajectory experts for different chromatic regimes, improving generalization to heterogeneous data with complex illumination and materials. Experiments show that NCT reduces artifacts and achieves more stable color transfer than prior flow-based methods, especially on 3D-rendered or highly textured images. The code is provided in supplementary materials.