AI Paper Atlas

Research map / 3D vision / Depth and stereo

A Simple Framework for 3D Lensless Imaging With Programmable Masks

Yucheng Zheng, Yi Hua, Aswin C. Sankaranarayanan, M. Salman Asif

ICCV 2021 · 3D vision › Depth and stereo · approach: Non-line-of-sight imaging · 12 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 trained U-Net instead of BM3D plus local contrast (ablation)post-processing · Lensless camera prototypetime: 47.85 seconds -> 0.0043 secondsImproved
use U-Net instead of BM3D plus local contrast (ablation)post-processing · Lensless camera prototypeimage sharpnessMixed
use Fourier-domain multi-plane recovery with 8 learned masks instead of SweepCam3D lensless recovery · Lensless camera prototypereconstruction time: 0.82 -> 0.33 secondsImproved
use learned mask patterns instead of MLS, shifted MLS or random masks (ablation)mask design · Middlebury simulation (5 scenes)SSIM and depth accuracyImproved
increase number of masks K (ablation)Fourier-domain recovery · Middlebury simulation (5 scenes)SSIM and depth accuracyImproved
use 8 learned masks with proposed recovery instead of SweepCam with 8 shifted MLS masks3D lensless recovery · Lensless camera prototypedepth plane qualityImproved

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