LensStyle：学习光学美学以实现可控风格化镜头效果渲染

中文摘要 AI 辅助

照片的视觉美学深受光圈形状、光学渐晕和光学衍射等镜头特性的影响，这些特性共同定义了相机独特的光学风格。现有的镜头效果渲染方法主要关注准确模拟从小光圈到大光圈的模糊过渡，但忽略了镜头效果的风格化方面，因此无法在大光圈下生成多样的焦外成像（bokeh）效果，也无法捕捉小光圈下出现的星芒（starbursts）等独特摄影现象。在本研究中，我们提出了LensStyle，这是一个用于可控风格化镜头效果渲染的统一框架，通过联合连续-离散控制明确建模镜头美学。我们的模型包含一个双路径控制器（Dual-Path Controller），它将连续光学参数调制（如对焦距离和模糊强度）与离散镜头风格条件（如圆形、多边形、甜甜圈、猫眼和星芒效果）解耦，支持在单个统一框架内进行细粒度、可解释且基于物理的镜头操控。为支持模型训练，我们整理了一个全面的MultiLens数据集，其中包含在真实光学约束下合成的多镜头图像对。大量实验表明，与现有的镜头效果渲染方法以及基于扩散的图像编辑模型相比，LensStyle实现了更出色的真实性、可控性和美学质量，推动计算摄影向多镜头风格模拟方向发展。

英文摘要

The visual aesthetics of photographs are deeply influenced by lens characteristics such as aperture shape, optical vignetting and optical diffraction, which together define a camera's unique optical style. Existing lens effect rendering methods primarily focus on accurately simulating the blur transition from small to large apertures but overlook the stylistic aspects of lens effects. As a result, they fail to produce diverse bokeh effects under large apertures or capture distinctive photographic phenomena such as starbursts that emerge under small apertures. In this work, we introduce LensStyle, a unified framework for controllable stylized lens effect rendering that explicitly models lens aesthetics through joint continuous-discrete control. Our model incorporates a Dual-Path Controller that disentangles continuous optical parameter modulation (e.g., focus distance and blur strength) from discrete lens-style conditioning (e.g., circular, polygonal, donut, cat-eye, and starburst effects), enabling fine-grained, interpretable, and physically grounded lens manipulation within a single unified framework. To support model training, we curate a comprehensive MultiLens dataset containing multi-lens image pairs synthesized under real optical constraints. Extensive experiments demonstrate that LensStyle achieves superior realism, controllability, and aesthetic quality compared with existing lens effect rendering approaches and diffusion-based image editing models, advancing computational photography toward multiple-lens-style simulation.

发表机构

• School of AIA, Huazhong University of Science and Technology（华中科技大学AIA学院）

机构由 AI 辅助整理，请以论文原文为准。