Research map / Image generation / Editing and style transfer
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
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace flow matching with direct latent regression (ablation) | LensStyle · MultiLens ablation | PSNR: 23.38 -> 21.87 | Hurt |
| add continuous optical parameter modulation (FiLM-style scale/shift) (ablation) | LensStyle · MultiLens ablation | PSNR: 22.14 -> 23.38 | Improved |
| add discrete style cross-attention (ablation) | LensStyle · MultiLens ablation | LPIPS: 0.2195 -> 0.1718 | Improved |
| retrain image editors on MultiLens | SuperEdit · MultiLens hexagon | PSNR: 17.27 -> 22.77 | Improved |
| use lens-aware Dual Path Controller instead of retrained SuperEdit | LensStyle · MultiLens styles | PSNR: 22.77 -> 23.38 | Improved |
| use LensStyle vs BokehDiff for circular bokeh | LensStyle · EBB400 | SSIM: 0.8029 -> 0.7892 | Hurt |
| use LensStyle vs BokehDiff for circular bokeh | LensStyle · MultiLens-Circle | LPIPS: 0.2368 -> 0.1743 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- SuperEdit* — SuperEdit: Rectifying and Facilitating Supervision for Instruction-Based Image Editing (ICCV 2025) · better on 15 of 15 shared results
- BokehDiff — BokehDiff: Neural Lens Blur with One-Step Diffusion (ICCV 2025) · better on 2 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- The Photographer's Eye: Teaching Multimodal Large Language Models to See, and Critique Like Photographers (CVPR 2025 · similarity 0.85)
- AKiRa: Augmentation Kit on Rays for Optical Video Generation (CVPR 2025 · similarity 0.84)
- StyLitGAN: Image-Based Relighting via Latent Control (CVPR 2024 · similarity 0.84)
- ReGS: Reference-based Controllable Scene Stylization with Gaussian Splatting (NeurIPS 2024 · similarity 0.83)
- Dr. Bokeh: DiffeRentiable Occlusion-aware Bokeh Rendering (CVPR 2024 · similarity 0.83)
- FPRF: Feed-Forward Photorealistic Style Transfer of Large-Scale 3D Neural Radiance Fields (AAAI 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
