AI Paper Atlas

Research map / 3D vision / Depth and stereo

Learning Rank-1 Diffractive Optics for Single-Shot High Dynamic Range Imaging

CVPR 2020 · 3D vision › Depth and stereo · approach: Spike and event camera reconstruction · 96 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 the jointly optimized rank-1 DOE and tailored reconstruction networksingle-shot HDR imaging · Test setPSNR: 48.26 vs. 40.30Helped
replace the proposed reconstruction network with Deep Optics (ablation)learned PSF HDR reconstruction · Test setPSNR: 48.26 -> 37.91Hurt
replace the proposed reconstruction network with HDR-CNN (ablation)learned PSF HDR reconstruction · Test setPSNR: 48.26 -> 33.51Hurt
replace the learned PSF with Dual Peak PSF (ablation)proposed reconstruction network · Test setPSNR: 48.26 -> 43.08Hurt
replace the learned PSF with Star PSF (ablation)proposed reconstruction network · Test setPSNR: 48.26 -> 42.62Hurt
replace the learned PSF with Dirac PSF (ablation)proposed reconstruction network · Test setPSNR: 48.26 -> 37.25Hurt
constrain the DOE height map to a rank-1 phase patternsingle-shot HDR imaging · Simulation test setPSNR: more than 7 dBHelped

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