Learning Texture Transformer Network for Image Super-Resolution
- URL: http://arxiv.org/abs/2006.04139v2
- Date: Mon, 22 Jun 2020 12:19:51 GMT
- Title: Learning Texture Transformer Network for Image Super-Resolution
- Authors: Fuzhi Yang, Huan Yang, Jianlong Fu, Hongtao Lu, Baining Guo
- Abstract summary: We propose a Texture Transformer Network for Image Super-Resolution (TTSR)
TTSR consists of four closely-related modules optimized for image generation tasks.
TTSR achieves significant improvements over state-of-the-art approaches on both quantitative and qualitative evaluations.
- Score: 47.86443447491344
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We study on image super-resolution (SR), which aims to recover realistic
textures from a low-resolution (LR) image. Recent progress has been made by
taking high-resolution images as references (Ref), so that relevant textures
can be transferred to LR images. However, existing SR approaches neglect to use
attention mechanisms to transfer high-resolution (HR) textures from Ref images,
which limits these approaches in challenging cases. In this paper, we propose a
novel Texture Transformer Network for Image Super-Resolution (TTSR), in which
the LR and Ref images are formulated as queries and keys in a transformer,
respectively. TTSR consists of four closely-related modules optimized for image
generation tasks, including a learnable texture extractor by DNN, a relevance
embedding module, a hard-attention module for texture transfer, and a
soft-attention module for texture synthesis. Such a design encourages joint
feature learning across LR and Ref images, in which deep feature
correspondences can be discovered by attention, and thus accurate texture
features can be transferred. The proposed texture transformer can be further
stacked in a cross-scale way, which enables texture recovery from different
levels (e.g., from 1x to 4x magnification). Extensive experiments show that
TTSR achieves significant improvements over state-of-the-art approaches on both
quantitative and qualitative evaluations.
Related papers
- Image Reconstruction using Enhanced Vision Transformer [0.08594140167290097]
We propose a novel image reconstruction framework which can be used for tasks such as image denoising, deblurring or inpainting.
The model proposed in this project is based on Vision Transformer (ViT) that takes 2D images as input and outputs embeddings.
We incorporate four additional optimization techniques in the framework to improve the model reconstruction capability.
arXiv Detail & Related papers (2023-07-11T02:14:18Z) - A Feature Reuse Framework with Texture-adaptive Aggregation for
Reference-based Super-Resolution [29.57364804554312]
Reference-based super-resolution (RefSR) has gained considerable success in the field of super-resolution.
We propose a feature reuse framework that guides the step-by-step texture reconstruction process.
We introduce a single image feature embedding module and a texture-adaptive aggregation module.
arXiv Detail & Related papers (2023-06-02T12:49:22Z) - Super-Resolution of License Plate Images Using Attention Modules and
Sub-Pixel Convolution Layers [3.8831062015253055]
We introduce a Single-Image Super-Resolution (SISR) approach to enhance the detection of structural and textural features in surveillance images.
Our approach incorporates sub-pixel convolution layers and a loss function that uses an Optical Character Recognition (OCR) model for feature extraction.
Our results show that our approach for reconstructing these low-resolution synthesized images outperforms existing ones in both quantitative and qualitative measures.
arXiv Detail & Related papers (2023-05-27T00:17:19Z) - Bridging Component Learning with Degradation Modelling for Blind Image
Super-Resolution [69.11604249813304]
We propose a components decomposition and co-optimization network (CDCN) for blind SR.
CDCN decomposes the input LR image into structure and detail components in feature space.
We present a degradation-driven learning strategy to jointly supervise the HR image detail and structure restoration process.
arXiv Detail & Related papers (2022-12-03T14:53:56Z) - Learning Detail-Structure Alternative Optimization for Blind
Super-Resolution [69.11604249813304]
We propose an effective and kernel-free network, namely DSSR, which enables recurrent detail-structure alternative optimization without blur kernel prior incorporation for blind SR.
In our DSSR, a detail-structure modulation module (DSMM) is built to exploit the interaction and collaboration of image details and structures.
Our method achieves the state-of-the-art against existing methods.
arXiv Detail & Related papers (2022-12-03T14:44:17Z) - RRSR:Reciprocal Reference-based Image Super-Resolution with Progressive
Feature Alignment and Selection [66.08293086254851]
We propose a reciprocal learning framework to reinforce the learning of a RefSR network.
The newly proposed module aligns reference-input images at multi-scale feature spaces and performs reference-aware feature selection.
We empirically show that multiple recent state-of-the-art RefSR models can be consistently improved with our reciprocal learning paradigm.
arXiv Detail & Related papers (2022-11-08T12:39:35Z) - Reference-based Image Super-Resolution with Deformable Attention
Transformer [62.71769634254654]
RefSR aims to exploit auxiliary reference (Ref) images to super-resolve low-resolution (LR) images.
This paper proposes a deformable attention Transformer, namely DATSR, with multiple scales.
Experiments demonstrate that our DATSR achieves state-of-the-art performance on benchmark datasets.
arXiv Detail & Related papers (2022-07-25T07:07:00Z) - Rethinking Super-Resolution as Text-Guided Details Generation [21.695227836312835]
We propose a Text-Guided Super-Resolution (TGSR) framework, which can effectively utilize the information from the text and image modalities.
The proposed TGSR could generate HR image details that match the text descriptions through a coarse-to-fine process.
arXiv Detail & Related papers (2022-07-14T01:46:38Z) - MASA-SR: Matching Acceleration and Spatial Adaptation for
Reference-Based Image Super-Resolution [74.24676600271253]
We propose the MASA network for RefSR, where two novel modules are designed to address these problems.
The proposed Match & Extraction Module significantly reduces the computational cost by a coarse-to-fine correspondence matching scheme.
The Spatial Adaptation Module learns the difference of distribution between the LR and Ref images, and remaps the distribution of Ref features to that of LR features in a spatially adaptive way.
arXiv Detail & Related papers (2021-06-04T07:15:32Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.