AI Paper Atlas

Research map / 3D vision / Depth and stereo

Deep Optics for Single-Shot High-Dynamic-Range Imaging

CVPR 2020 · 3D vision › Depth and stereo · approach: Spike and event camera reconstruction · 152 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
jointly optimize an optical PSF with the reconstruction CNN instead of using a conventional LDR captureSingle-shot HDR imaging · Test setPSNR-L: 39.8 -> 45.6Helped
encode scene information with a jointly learned PSF rather than reconstructing directly from LDRSingle-shot HDR imaging · Test setHDR-VDP-2: 58.6 -> 60.6Helped
use an end-to-end learned PSF instead of the heuristic star-shaped PSFU-Net HDR reconstruction · Test setPSNR-L: 42.1 -> 45.6Helped
remove physically realizable optical-element constraints (ablation)E2E PSF + U-Net · Test setHDR-VDP-2: 60.6 -> 67.1Helped
remove physically realizable optical-element constraints (ablation)E2E PSF + U-Net · Test setPSNR-L: 45.6 -> 46.8Helped
remove physically realizable optical-element constraints (ablation)E2E PSF + U-Net · Test setPSNR-γ: 44.3 -> 40.7Hurt
use per-batch gamma-corrected L2 norms rather than the previously tried tone-mapped L2 loss (ablation)E2E PSF training · HDR image reconstructionPSF qualityHelped

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