Learning Lens Blur Fields
Esther Y. H. Lin, Zhecheng Wang, Rebecca Lin, Daniel Miau, Florian Kainz, Jiawen Chen, Xuaner Cecilia Zhang, David B. Lindell, Kiriakos N. Kutulakos

TL;DR
This paper introduces a neural representation called the lens blur field, which models complex optical blur variations across different camera settings and devices, enabling accurate characterization of lens behavior.
Contribution
We propose a high-dimensional neural model for lens blur fields and a method to learn them from focal stacks, capturing device-specific optical effects in a parametric form.
Findings
The lens blur field accurately models optical variations across image plane, focus, and depth.
The method can distinguish optical differences between similar smartphone devices.
A new dataset of 5D blur fields for various cameras is provided.
Abstract
Optical blur is an inherent property of any lens system and is challenging to model in modern cameras because of their complex optical elements. To tackle this challenge, we introduce a high-dimensional neural representation of blurand a practical method for acquiring it. The lens blur field is a multilayer perceptron (MLP) designed to (1) accurately capture variations of the lens 2D point spread function over image plane location, focus setting and, optionally, depth and (2) represent these variations parametrically as a single, sensor-specific function. The representation models the combined effects of defocus, diffraction, aberration, and accounts for sensor features such as pixel color filters and pixel-specific micro-lenses. To learn the real-world blur field of a given device, we formulate a generalized non-blind deconvolution problem that…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage Processing Techniques and Applications · Advanced Image Processing Techniques · Advanced Vision and Imaging
MethodsSparse Evolutionary Training · Focus
