AI Paper Atlas

Research map / Video / Video segmentation and tracking

SASSI — Super-Pixelated Adaptive Spatio-Spectral Imaging

Vishwanath Saragadam, Michael DeZeeuw, Richard G. Baraniuk, Ashok Veeraraghavan, Aswin C. Sankaranarayanan

TPAMI 2021 · Video › Video segmentation and tracking · approach: Real-world video super-resolution · 28 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 the guide-image-based neural guided-filter reconstruction instead of rank-1 reconstructionSASSI real capture · Real captured scene (33 ms exposure)PSNR (dB): 41.5 -> 42.6Improved
use a guide image in reconstructionSASSI vs non-guide methods · SimulationPSNR (dB): outperforms other approaches by more than 2dBImproved
use larger superpixels at low light, smaller at high light (ablation)SASSI · Simulation, varying noisereconstruction accuracyMixed
use guided filtering instead of rank-1 at low light (ablation)SASSI · Simulation, low lightreconstruction accuracyImproved
learn all guided filters and refinement jointly (8 filters plus refinement) versus single naive or partial variants (ablation)SASSI neural reconstruction · ICVLPSNR and SSIMImproved

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