Training-Free Model Ensemble for Single-Image Super-Resolution via Strong-Branch Compensation

TL;DR

This paper introduces a training-free ensemble method for single-image super-resolution that combines outputs from pretrained models to improve performance without additional training.

Contribution

It proposes a novel output-level ensemble framework using a dual-branch pipeline with no extra training or parameter updates, enhancing super-resolution results.

Findings

Consistently improves PSNR over base models in super-resolution tasks.

Slightly exceeds the performance of the strongest individual branch.

Ablation studies confirm the effectiveness and practicality of output-level compensation.

Abstract

Single-image super-resolution has progressed from deep convolutional baselines to stronger Transformer and state-space architectures, yet the corresponding performance gains typically come with higher training cost, longer engineering iteration, and heavier deployment burden. In many practical settings, multiple pretrained models with partially complementary behaviors are already available, and the binding constraint is no longer architectural capacity but how effectively their outputs can be combined without additional training. Rather than pursuing further architectural redesign, this paper proposes a training-free output-level ensemble framework. A dual-branch pipeline is constructed in which a Hybrid attention network with TLC inference provides stable main reconstruction, while a MambaIRv2 branch with geometric self-ensemble supplies strong compensation for high-frequency detail recovery. The two branches process the same low-resolution input independently and are fused in the image space via a lightweight weighted combination, without updating any model parameters or introducing an additional trainable module. As our solution to the NTIRE 2026 Image Super-Resolution ($\times 4$) Challenge, the proposed design consistently improves over the base branch and slightly exceeds the pure strong branch in PSNR at the best operating point under a unified DIV2K bicubic $\times 4$ evaluation protocol. Ablation studies confirm that output-level compensation provides a low-overhead and practically accessible upgrade path for existing super-resolution systems.