AI Paper Atlas

Research map / 3D vision / Depth and stereo

Physics-Free Spectrally Multiplexed Photometric Stereo under Unknown Spectral Composition

Satoshi Ikehata, Yuta Asano

ECCV 2024 · 3D vision › Depth and stereo · approach: Snapshot hyperspectral imaging · 1 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 SpectraM-PS physics-free network trained on RGB-rendered PS-Multiplex instead of calibrated physics-based methodsSpectraM-PS · SpectraM14 Condition 1mean angular error (deg): 17.1 -> 8.9Improved
increase channel crosstalk (Condition 1 to 3) for SpectraM-PSSpectraM-PS · SpectraM14mean angular error (deg): 8.9 -> 11.6Hurt
increase channel crosstalk (Condition 1 to 3) for Guo et al.Guo et al. · SpectraM14mean angular error (deg): 18.9 -> 51.7Hurt
train on RGB-only narrowband rendered data then test on NIR sensorsSpectraM-PS · SpectraM14 Condition 4 (NIR)mean angular error (deg): 19.1 -> 8.4Improved
SpectraM-PS vs SDM-UniPS trained on PS-Multiplex (dual-scale decoder with patch embedding) (ablation)SpectraM-PS · synthetic spectrally multiplexed scenesmean angular error (deg)Improved
SpectraM-PS is slower than Lv et al. at inferenceSpectraM-PS · SpectraM14 Conditions 2 and 3inference time (sec): 0.46 -> 3.42Hurt

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