AI Paper Atlas

Research map / 3D vision / Depth and stereo

Differentiable Programming for Hyperspectral Unmixing using a Physics-based Dispersion Model

John Janiczek, Parth Thaker, Gautam Dasarathy, Christopher S. Edwards, Philip Christensen, Suren Jayasuriya

ECCV 2020 · 3D vision › Depth and stereo · approach: Snapshot hyperspectral imaging · 4 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 dispersion-model analysis-by-synthesis instead of NCMNCM · Feely (lab IR, 90 test samples)abundance MSE: 0.119 -> 0.052Improved
train deep models on synthetic data with limited real dataCNN-1D · Feely (lab IR, 90 test samples)abundance MSE: 0.205 -> 0.052 vs analysis-by-synthesisHurt
add generative dispersion model to CNN output (Inverse Rendering vs CNN-1D Modified)CNN-1D Modified · Gulfport (VNIR aerial)abundance MSE: 0.297 -> 0.272Improved
add generative dispersion model to CNN output (Inverse Rendering vs CNN-1D Modified)CNN-1D Modified · Gulfport synthetic mixturesabundance MSE: 0.148 -> 0.059Improved
add generative dispersion model to CNN output (Inverse Rendering vs CNN-1D Modified)CNN-1D Modified · Feely (lab IR, 90 test samples)abundance MSE: 0.205 -> 0.188 (both worse than analysis-by-synthesis 0.052)Hurt
use analysis-by-synthesis (no training data) instead of FCLSFCLS · Gulfport (VNIR aerial)abundance MSE: 0.75 -> 0.45Improved
use BCM statistical variability model instead of analysis-by-synthesisAnalysis-by-synthesis · Gulfport synthetic mixturesabundance MSE: 0.147 -> 0.136No clear effect
use analysis-by-synthesis on Mars TES data instead of FCLSFCLS · Mars TES dataRMS reconstruction error: 0.0043 -> 0.0038Improved
use alternating minimization instead of joint optimization of abundances and dispersion parametersjoint optimization · Feelyspeed and convergenceImproved
add dispersion-model analysis-by-synthesis runtime cost versus FCLSFCLS · Unmixing speed (averaged over 90 mixtures)time per operation: 10ms -> 10.2sHurt
add noise to input, methods trained without noiseCNN and Inverse Rendering · Feely noise test (30 samples)abundance MSE under noiseHurt

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