AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Convolutional Approximations to the General Non-Line-of-Sight Imaging Operator

Byeongjoo Ahn, Akshat Dave, Ashok Veeraraghavan, Ioannis Gkioulekas, Aswin C. Sankaranarayanan

ICCV 2019 · Learning theory and algorithms › Matrix and tensor methods · approach: Signal recovery and phase retrieval · 67 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
solve the Gram-operator deconvolution instead of full linear reconstructionNLOS reconstruction (S-shape, 5D transient) · Simulated S-shape sceneruntime: 70x faster with similar reconstruction qualityImproved
use exact inverse kernel deconvolution instead of Laplacian filtered backprojectionOurs (w/o priors) · Simulated Stanford bunnymean absolute depth error (cm): 1.01 cm -> 0.99 cmImproved
use exact inverse kernel deconvolution instead of Laplacian filtered backprojectionOurs (w/o priors) · Simulated Stanford bunnyroot mean square depth error (cm): 2.38 cm -> 2.33 cmImproved
use Gram-based method at 0.24 cm voxels instead of LCT at 0.78 cm voxelsOurs (w/o priors) · Simulated Stanford bunnymean absolute depth error (cm): 1.12 cm -> 0.99 cmImproved
add positivity, total variation and sparsity priors (ablation)Gram-based NLOS reconstruction · Real confocal transientreconstruction quality (qualitative)Improved
use the Gram method without priors instead of filtered backprojectionGram-based NLOS reconstruction · Real confocal transientreconstruction quality (qualitative)Improved
use Gram-based method instead of LCT at low scanning resolutionGram-based NLOS reconstruction · Rendered confocal transient, 64x64 scan on 0.5 m walllateral detail (qualitative)Improved

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