AI Paper Atlas

Research map / Image generation / Image restoration

Filterless Snapshot Hyperspectral Imaging using Guided Patch Diffusion

Dean Hazineh, Luca Sacchi, Davide Cassara, Federico Capasso, Todd Zickler

ECCV 2026 · Image generation › Image restoration · approach: Pansharpening and spectral fusion · 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
add PSF-consistency guidance during sampling (ablation)patch diffusion (64px) · ARAD1K filterlessPSNR: 32.32 -> 34.6Improved
add guidance with 32px patches (ablation)patch diffusion (32px) · ARAD1K filterlessPSNR: 29.27 -> 33.27Improved
reduce patch size from 64 to 32 (equal to PSF width), with guidance (ablation)patch diffusion · ARAD1K filterlessPSNR: 34.7 -> 33.3Hurt
use overlapping patches (stride 32) with guidance (ablation)patch diffusion (64px) · ARAD1K filterlessPSNR: 34.7 -> 34.8No clear effect
use overlapping patches without guidance (ablation)patch diffusion (64px) · ARAD1K filterlessPSNR: 32.2 -> 33.0Improved
compute per-patch scale by least squares during sampling instead of no rescaling (ablation)patch diffusion (64px, guided) · ARAD1K filterlessPSNR: 31.8 -> 34.7Improved
use patch diffusion instead of full-field UNet regression (ablation)UNet backbone · ARAD1K filterlessPSNR: 29.12 -> 34.6Improved
increase guidance iterations from 20 to 60 (ablation)Ours · ARAD1K filterlessPSNR: 32.32 (none) -> 35.22 (60 iters)Improved
use strongly dispersive PSF designs R2/R3 instead of R1 (ablation)Ours · ARAD1K lens comparisonPSNR: 35.0 -> 34.0 (R2), 34.1 (R3)Hurt
use chromatic-aberration PSF R1 instead of all-in-focus lens (ablation)Ours · ARAD1K lens comparisonPSNR: 29.8 -> 35.0Improved
patch diffusion vs best full-field baseline (SST)Ours · ARAD1K filterlessPSNR: 31.8 -> 34.6Improved
apply model trained on ARAD1K to ICVL/Harvard without finetuningOurs · ICVL, HarvardPSNR: 33.48 (ICVL), 32.37 (Harvard)Mixed

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