arXiv Computer Vision By Yachuan Huang, Liwen Xiao, Liao Shen, Qiwen Wang, Huiqiang Sun, Zhiyu Pan, Zhiguo Cao

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

Read the original on arXiv Computer Vision →

LensStyle is a unified framework for controllable stylized lens effect rendering that explicitly models lens aesthetics through joint continuous‑discrete control. It uses a Dual‑Path Controller to separate continuous optical parameter modulation (e.g., focus distance, blur strength) from discrete lens‑style conditioning (e.g., circular, polygonal, donut, cat‑eye, starburst effects), allowing fine‑grained, interpretable, and physically grounded manipulation. The authors also curate a MultiLens dataset of multi‑lens image pairs synthesized under real optical constraints, and experiments show LensStyle outperforms existing lens effect rendering methods and diffusion‑based image editing models in realism, controllability, and aesthetic quality.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv Computer Vision
Aug 21

Unwarping the Lens: A Physics-Grounded Approach to Video Glasses Removal

arXiv:2608. 20212v1 Announce Type: new Abstract: High-fidelity removal of eyeglasses from video is a major challenge in facial attribute editing, as the underlying facial geometry is often obscured by complex refractive distortions and view-dependent specular reflections.

By Radim Spetlik, David Futschik, Radek Danecek, Feitong Tan, Ziqian Bai, Rohit Pandey, Yinda Zhang
Hugging Face Trending Papers
Jul 7

Realistic Compound-Lens Defocus Blur Synthesis

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.

arXiv AI
Sep 10

Aes3D: Aesthetic Assessment in 3D Gaussian Splatting

arXiv:2605.05155v4 Announce Type: replace-cross Abstract: As 3D Gaussian Splatting (3DGS) gains attention in immersive media and digital content creation, assessing the aesthetics of 3D scenes become...

By Chuanzhi Xu, Boyu Wei, Haoxian Zhou, Xuanhua Yin, Zihan Deng, Haodong Chen, Qiang Qu, Weidong Cai
arXiv Machine Learning
Jun 3

Towards Blind Lens Aberration Correction via Large LensLib Pre-training and Discrete Degradation Priors

arXiv:2511. 17126v4 Announce Type: replace-cross Abstract: Emerging deep-learning-based lens library pre-training (LensLib-PT) pipeline offers a new avenue for blind lens aberration correction by training a universal neural network, demonstrating strong capability in handling diverse unknown optical degradations.

By Xiaolong Qian, Qi Jiang, Yao Gao, Lei Sun, Kailun Yang, Xian Wang, Zhonghua Yi, Wenyong Li, Ming-Hsuan Yang, Luc Van Gool, Kaiwei Wang
arXiv AI
Jun 30

InsertAnywhere: Geometrically Grounded and Optics-Aware Video Object Insertion

arXiv:2512. 17504v2 Announce Type: replace-cross Abstract: Recent advances in diffusion models have enabled impressive video editing capabilities, yet production-grade Video Object Insertion (VOI) remains challenging due to inadequate 4D scene understanding and a lack of proper optical interactions, such as shadows and reflections.

By Hoiyeong Jin, Hyojin Jang, Junha Hyung, Jeongho Kim, Kinam Kim, Dongjin Kim, Huijin Choi, Hyeonji Kim, Jaegul Choo