Image super-resolution reconstruction based on instance spatial feature modulation and feedback mechanism

Abstract

Image super-resolution reconstruction is a research hotspot in the field of computer vision. Traditional image super-resolution reconstruction methods based on deep learning mostly up-sample low-resolution images ignoring categories and instances, which will cause some problems such as unrealistic texture in the reconstructed images or sawtooth phenomenon on the edge of instance. In this manuscript, we propose an image super-resolution reconstruction method based on instance spatial feature modulation and feedback mechanism. First, the prior knowledge of instance spatial features is introduced in the reconstruction process. Instance spatial features of low-resolution images are extracted to modulate super-resolution reconstruction features. Then, based on the feedback mechanism, the modulated low-resolution image features are iteratively optimized for the reconstruction results, so that the model can finally learn instance-level reconstruction ability. Experiments on COCO-2017 show that, compared with traditional deep learning-based image super-resolution reconstruction methods, the proposed method can obtain better image reconstruction results, and the reconstructed images have more realistic instance textures.