ECBANet: Exploiting Complementary Information for Efficient Burst Super-Resolution

Abstract

Multi-frame Super-Resolution (MFSR) aims to reconstruct a high-resolution (HR) image from a sequence of burst images, thereby overcoming the information scarcity limitations inherent in Single Image Super-Resolution (SISR). In this paper, we propose ECBANet, unlike most existing approaches, we employ an efficient and lightweight Pre-Alignment module to select sharp frames and align multiple frames, and we emphasize the complementarity between frames and introduce the Complementary Affinity Fusion (CAF) module. To better harness the complementarity of burst images in conjunction with CAF, we propose the Flexible Expansion Recursive Fusion (FlexERF) module, which finely and efficiently fuses features from arbitrary frames through its two sub-modules: the Recursive Fusion module and the Expansion Fusion module. Finally, we have conducted extensive experiments on different MFSR datasets, and the results show that our ECBANet surpasses existing state-of-the-art burst super-resolution methods.