A dual-branch training-free ensemble fuses a hybrid attention network with a Mamba-based model via weighted combination to enhance super-resolution PSNR on DIV2K x4.
Srconvnet: A transformer-style con- vnet for lightweight image super-resolution.International Journal of Computer Vision, 133(1):173–189, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Training-Free Model Ensemble for Single-Image Super-Resolution via Strong-Branch Compensation
A dual-branch training-free ensemble fuses a hybrid attention network with a Mamba-based model via weighted combination to enhance super-resolution PSNR on DIV2K x4.