AI Paper Atlas

Research map / 3D vision / Depth and stereo

Divide and Conquer for Full-Resolution Light Field Deblurring

M. R. Mahesh Mohan, A. N. Rajagopalan

CVPR 2018 · 3D vision › Depth and stereo · approach: Neural light field and illumination imaging · 8 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
Decompose LF deblurring into blind deblurring of one subaperture image and non-blind deblurring of the others using a shared MDFFull-resolution light field deblurring · LF {433, 625, 15, 15}runtime: Not feasible -> 38 minsImproved
Use a shared MDF and independent 2D subproblems instead of joint 4D optimizationLight field deblurring · LF {200, 200, 8, 8}runtime: 2 hrs, 20 mins -> 8.21 minsImproved
Use a shared MDF and independent 2D subproblems instead of joint 4D optimizationLight field deblurring · LF {200, 289, 8, 8}runtime: 3 hrs, 17 mins -> 12.62 minsImproved
Use the proposed MDF model for wide-angle and irregular camera motionLight field deblurring · Wide-angle and vibration trajectoriesIFCImproved
Use the proposed MDF model for wide-angle and irregular camera motionLight field deblurring · Wide-angle and vibration trajectoriesVIFImproved

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