AI Paper Atlas

Research map / 3D vision / Depth and stereo

Learning Lens Blur Fields

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

TPAMI 2025 · 3D vision › Depth and stereo · approach: Neural light field and illumination imaging · 13 citations (OpenAlex)

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 changedWhereMeasuredEffect
use proposed MLP blur field instead of Mannan & LangerPSF estimation · Synthetic, validation lens positionsPSNR: 15.291 -> 30.462Improved
use proposed MLP blur field instead of Joshi et al.PSF estimation · Synthetic, validation lens positions, validation patternsPSNR: 28.964 -> 30.396Improved
use proposed MLP blur field instead of Joshi et al.PSF estimation · Synthetic, validation lens positions, training patternsPSNR: 30.797 -> 30.462Hurt
use proposed MLP blur field instead of Joshi et al.PSF estimation · Synthetic, training lens positions, training patternsSSIM: 0.950 -> 0.929Hurt
use MLP interpolation instead of linear interpolation of MLP PSFs (ablation)lens blur field · Synthetic, validation lens positions, training patternsPSNR: 29.394 -> 30.462Improved
use MLP interpolation instead of linear interpolation of MLP PSFs (ablation)lens blur field · Synthetic, validation lens positions, validation patternsSSIM: 0.887 -> 0.919Improved
use blur field PSFs instead of Seidel model PSFs (ablation)image restoration · Siemens Star restorationPSNR: 7.415 -> 8.900Improved
use blur field PSFs instead of Seidel model PSFs (ablation)image restoration · Siemens Star restorationSSIM: 0.127 -> 0.293Improved
use blur field PSFs instead of Seidel model PSFs (ablation)image restoration · Synthetic blurry image (Blue channel)PSNR: 17.754 -> 17.700Hurt
use MLP representation instead of discrete 5D PSF optimizationPSF acquisition · 5D PSF, iPhone 12 Prooptimization time: 34 days -> 14 hoursImproved
use MLP representation instead of discrete 5D PSF storagePSF acquisition · 5D PSF, iPhone 12 Promemory: 9.3GB -> 19.1MBImproved
add target distance dimension (6D instead of 5D blur field)lens blur field · iPhone 12 Pro widePSF variationNo clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy