AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Hyperspectral and Multispectral Image Fusion with Arbitrary Resolution Through Self-Supervised Representations

Ting Wang, Zipei Yan, Jizhou Li, Xi-Le Zhao, Chao Wang, Michael K. Ng

IJCV 2025 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 15 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 TV loss (ablation)CLoRF · Pavia UniversityMPSNR: 41.48 -> 42.23Improved
add TV loss (ablation)CLoRF · University of HoustonMPSNR: 39.04 -> 40.55Improved
use Sine activation instead of ReLU (ablation)CLoRF · Pavia UniversityMPSNR: 25.92 -> 42.23Improved
use Sine activation instead of ReLU+PE (ablation)CLoRF · Pavia UniversityMPSNR: 36.26 -> 42.23Improved
use Sine activation instead of Spder (ablation)CLoRF · University of HoustonMPSNR: 39.16 -> 40.55Improved
increase downsampling ratio from 4 to 16CLoRF · Pavia UniversityMPSNR: 42.23 -> 41.11Hurt
blind estimation of PSF and SRF instead of semi-blindCLoRF · Pavia UniversityMPSNR: 41.40 -> 38.98Hurt
self-supervised CLoRF versus supervised MCT-NetCLoRF · Pavia CenterMPSNR: 41.82 -> 43.47Improved
CLoRF versus bicubic for arbitrary spatial upsamplingCLoRF · Pavia University (336,336,50)MPSNR: 29.29 -> 29.22No clear effect
CLoRF versus bicubic for joint spectral and spatial upsamplingCLoRF · Pavia University (336,336,93)MPSNR: 27.48 -> 28.61Improved
CLoRF versus bicubic for arbitrary spectral upsamplingCLoRF · Pavia University (168,168,61)MPSNR: 37.64 -> 42.42Improved
CLoRF versus MSE-SURE on SAM at Pavia CenterCLoRF · Pavia CenterSAM: 3.51 -> 3.64Hurt

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