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

2026-04-13

AI Summary

This work addresses the challenge of effectively fusing multiple pre-trained super-resolution models to enhance reconstruction performance without incurring additional training costs. It proposes a training-free dual-branch inference framework, where a main branch ensures stable reconstruction and a strong branch compensates for high-frequency details. The two branches are integrated via a lightweight image-space weighted fusion mechanism at the output stage, leveraging a hybrid attention network combined with the MambaIRv2 architecture. Geometric self-ensemble and TLC (Test-Time Lightweight Calibration) inference strategies further refine the results. Evaluated on the DIV2K ×4 benchmark, the method achieves a PSNR superior to that of the main branch alone and slightly surpasses the strong branch used in isolation, demonstrating its effectiveness and practical utility.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Ensemble Methods
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data

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.

Problem

• single-image super-resolution
• model ensemble
• training-free
• output fusion
• high-frequency detail

Innovation

• training-free ensemble
• single-image super-resolution
• output-level fusion
• MambaIRv2
• hybrid attention network