LensStyle: Learning the Optical Aesthetics for Controllable Stylized Lens Effect Rendering

Yachuan Huang; Liwen Xiao; Liao Shen; Qiwen Wang; Huiqiang Sun; Zhiyu Pan; Zhiguo Cao

cs.CVSep 4, 2026

LensStyle: Learning the Optical Aesthetics for Controllable Stylized Lens Effect Rendering

Authors: Yachuan Huang, Liwen Xiao, Liao Shen, Qiwen Wang, Huiqiang Sun, Zhiyu Pan, Zhiguo Cao

Organizations: School of AIA, Huazhong University of Science and Technology, Wuhan, China

Abstract

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.

Figures & tables

Figure 1: Controllable multi-style lens effect rendering with LensStyle. Our framework enables unified control over three complementary dimensions of lens aesthetics within a single model. Top-left: continuous focus distance control, where the focal plane smoothly shifts from near to far. Top-right: continuous blur strength control, adjusting the magnitude of defocus under fixed focus. Bottom: discrete lens style control, synthesizing diverse aperture-induced effects including circular, hexagonal, donut, cat-eye bokeh, and diffraction-driven starburst patterns. These results demonstrate that LensStyle jointly models continuous optical parameters and discrete lens geometries in a physically grounded and interpretable manner.

Figure 2: Overview of LensStyle. The input image is first encoded into latent by a VAE encoder and then processed by a flow matching network for lens effect rendering. A Dual Path Controller conditions the generative backbone through two complementary branches. The Continuous Optical Parameter Modulation branch encodes user-specified optical parameters ( e.g . , focus distance and blur strength) into embeddings that generate adaptive scaling and shifting factors, which modulate intermediate image features for precise continuous control. In parallel, the Discrete Lens Style Cross-Attention branch encodes the selected lens style into text embeddings and injects style-specific information into the network via cross-attention. The denoised latent is finally decoded by the VAE decoder to produce the stylized output image.

Panel of Figure 3 — Figure 3: MultiLens Dataset Overview

Table 1: Quantitative comparison across polygonal, donut, cat-eye, and starburst styles on MultiLens dataset. Higher PSNR/SSIM and lower LPIPS are better. LensStyle constantly outperforms diffusion-based image editing methods.

Figure 4: Qualitative Comparison against bokeh rendering methods for standard circle bokeh. All baselines take a depth map predicted by Depth Anything V2 [ 48 ] as input. As a result, when depth map is inaccurate, the focused region of output can be blurred by mistake (green box area). Moreover, ours produces more aesthetically pleasing circle bokeh (blue box area).

Figure 5: Qualitative Comparison against diffusion-based image editing methods. UltraEdit and SuperEdit lack lens style awareness, resulting in outputs that do not match the specified lens style. After fine-tuning on our MultiLens dataset, these models begin to capture certain lens style characteristics. However, thanks to the proposed Dual Path Controller with its disentangled continuous-discrete conditioning mechanism, our method achieves the most consistent and visually superior results.

Figure 6: User study visual comparisons under focus distance $0.70$ and blur intensity $0.80$ with hexagonal aperture style. Our method produces hexagonal bokeh patterns that are geometrically consistent and physically plausible, whereas SuperEdit* [ 17 ] generates hexagons with overly sharp corner transitions.

Variant	Flow	COPM	DLSC	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$
w/o Flow (Direct Regression)		✓	✓	21.87	0.6822	0.2433
w/o OPM	✓		✓	22.14	0.7034	0.2126
w/o SCA	✓	✓		22.06	0.6951	0.2195
Full Model	✓	✓	✓	23.38	0.7389	0.1718

Table 4: Ablation study on the MultiLens dataset. We evaluate the contribution of each core component in LensStyle.

Computational Imaging

Computational imaging combines optical and sensor design with algorithms to recover or infer scene information from indirect, compressed, or noisy measurements.

See all 123 papers

Realistic Compound-Lens Defocus Blur Synthesis
Jul 7, 2026Yunkyu Lee, Woohyeok Kim, Sunghyun ChoImage Deblurring Synthetic Data Generation
POSTECH, Pohang, Korea
Style-Aware Gloss Control for Generative Non-Photorealistic Rendering
Feb 18, 2026Santiago Jimenez-Navarro, Belen Masia, Ana SerranoControllable Image Generation Disentangled Representation Learning
University of Zaragoza – I3A, Spain
Towards Photorealistic and Efficient Bokeh Rendering via Diffusion Framework
May 8, 2026Linxiao Shi, Siming Zheng, Zerong Wang +5Neural Rendering Image Super-Resolution
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · vivo BlueImage Lab, vivo Mobile Communication Co., Ltd. · Shenzhen University of Advanced Technology

Jul 7, 2026J/K move · Enter open · S save

Realistic Compound-Lens Defocus Blur Synthesis

Yunkyu Lee, Woohyeok Kim, Sunghyun Cho

POSTECH, Pohang, Korea

Image Deblurring Synthetic Data Generation Computational Imaging

Open paper AskPDF arXiv

Defocus blur degrades fine image structures and limits visual perception, which can adversely affect downstream vision tasks. Although recent deep learning deblurring methods have achieved strong performance, their effectiveness depends on training data and often degrades across cameras and lenses due to limited optical diversity and realism in existing datasets. In this paper, we propose a pipeline for synthesizing realistic defocus deblurring datasets for diverse compound lenses. It integrates efficient wave-optics PSF computation via Debye CZT propagation, depth-aware defocus rendering with occlusion handling, and blur synthesis in the radiometrically linear space with camera ISP simulation. This unified pipeline enables the scalable generation of photorealistic defocus datasets with diverse lens characteristics. Using our pipeline, we generate CLDefocus, a large-scale synthetic dataset containing lens-diverse defocus image pairs. We further analyze the limitations of real-captured defocus datasets and show that such imperfections can bias full-reference evaluation. Extensive experiments demonstrate that models trained on CLDefocus achieve improved cross-device generalization compared to models trained on existing real and synthetic datasets.

Abstract

Computational Imaging

Explore similar work

Realistic Compound-Lens Defocus Blur Synthesis

Style-Aware Gloss Control for Generative Non-Photorealistic Rendering

Towards Photorealistic and Efficient Bokeh Rendering via Diffusion Framework