Multi-Scale Implicit Transformer with Re-parameterize for Arbitrary-Scale Super-Resolution
Recently, the methods based on implicit neural representations have shown excellent capabilities for arbitrary-scale super-resolution (ASSR). Although these methods represent the features of an image by generating latent codes, these latent codes are difficult to adapt for different magnification factors of super-resolution, which seriously affects their performance. Addressing this, we design Multi-Scale Implicit Transformer (MSIT), consisting of an Multi-scale Neural Operator (MSNO) and Multi-Scale Self-Attention (MSSA). Among them, MSNO obtains multi-scale latent codes through feature enhancement, multi-scale characteristics extraction, and multi-scale characteristics merging. MSSA further enhances the multi-scale characteristics of latent codes, resulting in better performance. Furthermore, to improve the performance of network, we propose the Re-Interaction Module (RIM) combined with the cumulative training strategy to improve the diversity of learned information for the network. We have systematically introduced multi-scale characteristics for the first time in ASSR, extensive experiments are performed to validate the effectiveness of MSIT, and our method achieves state-of-the-art performance in arbitrary super-resolution tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversitySuper-ResolutionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Cascaded Local Implicit Transformer for Arbitrary-Scale Super-Resolution
Implicit neural representation has recently shown a promising ability in representing images with arbitrary resolutions. In this paper, we present a Local Implicit Transformer (LIT), which integrates the attention mechan…
Super-ResolutionLearning Continuous Representation of Audio for Arbitrary Scale Super Resolution
Audio super resolution aims to predict the missing high resolution components of the low resolution audio signals. While audio in nature is a continuous signal, current approaches treat it as discrete data (i.e., input i…
Audio Super-ResolutionSelf-Supervised LearningSuper-ResolutionRethinking Multi-Contrast MRI Super-Resolution: Rectangle-Window Cross-Attention Transformer and Arbitrary-Scale Upsampling
Recently, several methods have explored the potential of multi-contrast magnetic resonance imaging (MRI) super-resolution (SR) and obtain results superior to single-contrast SR methods. However, existing approaches s…
Super-ResolutionLocal Implicit Wavelet Transformer for Arbitrary-Scale Super-Resolution
Implicit neural representations have recently demonstrated promising potential in arbitrary-scale Super-Resolution (SR) of images. Most existing methods predict the pixel in the SR image based on the queried coordinate a…
Super-ResolutionDeepCurrents: Learning Implicit Representations of Shapes with Boundaries
Recent techniques have been successful in reconstructing surfaces as level sets of learned functions (such as signed distance fields) parameterized by deep neural networks. Many of these methods, however, learn only clos…