AI Paper Atlas

Research map / 3D vision / Depth and stereo

Single-Shot Hyperspectral-Depth Imaging With Learned Diffractive Optics

Seung-Hwan Baek, Hayato Ikoma, Daniel S. Jeon, Yuqi Li, Wolfgang Heidrich, Gordon Wetzstein, Min H. Kim

ICCV 2021 · 3D vision › Depth and stereo · approach: Snapshot hyperspectral imaging · 142 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
replace Fresnel DOE with end-to-end learned DOE (ablation)HS-D reconstruction network · HS-D datasetPSNR (dB): 27.96 -> 29.31Improved
replace Spiral DOE with end-to-end learned DOE (ablation)HS-D reconstruction network · HS-D datasetPSNR (dB): 26.90 -> 29.31Improved
replace Fisher DOE with end-to-end learned DOE (ablation)HS-D reconstruction network · HS-D datasetPSNR (dB): 28.51 -> 29.31Improved
replace Fisher DOE with end-to-end learned DOE (ablation)HS-D reconstruction network · HS-D datasetSSIM: 0.79 -> 0.81Improved
replace Fresnel DOE with end-to-end learned DOE (ablation)HS-D reconstruction network · HS-D datasetdepth MAE (m): 0.15 -> 0.12Improved
replace Fisher DOE with end-to-end learned DOE (ablation)HS-D reconstruction network · HS-D datasetdepth RMSE (m): 0.23 -> 0.20Improved
replace Spiral DOE with end-to-end learned DOE (ablation)HS-D reconstruction network · HS-D datasetdepth RMSE (m): 0.32 -> 0.20Improved
replace light-field compressive HS-D method (Feng et al.) with learned DOE (ablation)single-shot HS-D imaging · HS-D datasetPSNR (dB): 23.62 -> 29.31Improved
replace light-field compressive HS-D method (Feng et al.) with learned DOE (ablation)single-shot HS-D imaging · HS-D datasetdepth RMSE (m): 0.57 -> 0.20Improved
replace light-field compressive HS-D method (Feng et al.) with learned DOE (ablation)single-shot HS-D imaging · HS-D datasetSSIM: 0.76 -> 0.81Improved
replace light-field compressive HS-D method (Feng et al.) with learned DOE (ablation)single-shot HS-D imaging · HS-D datasetdepth MAE (m): 0.30 -> 0.12Improved
use Fisher-information DOE as initialization instead of Fresnel (CRLB discriminating power) (ablation)DOE design · CRLB analysisCRLB: 2.73 -> 1.36Improved

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