paper-with-me

홈 › Papers

Efficient Mixed Transformer for Single Image Super-Resolution

2023-05-19 · Ling Zheng, Jinchen Zhu, Jinpeng Shi, Shizhuang Weng

Recently, Transformer-based methods have achieved impressive results in single image super-resolution (SISR). However, the lack of locality mechanism and high complexity limit their application in the field of super-resolution (SR). To solve these problems, we propose a new method, Efficient Mixed Transformer (EMT) in this study. Specifically, we propose the Mixed Transformer Block (MTB), consisting of multiple consecutive transformer layers, in some of which the Pixel Mixer (PM) is used to replace the Self-Attention (SA). PM can enhance the local knowledge aggregation with pixel shifting operations. At the same time, no additional complexity is introduced as PM has no parameters and floating-point operations. Moreover, we employ striped window for SA (SWSA) to gain an efficient global dependency modelling by utilizing image anisotropy. Experimental results show that EMT outperforms the existing methods on benchmark dataset and achieved state-of-the-art performance. The Code is available at https://github.com/Fried-Rice-Lab/FriedRiceLab.

📄 PDF Abstract BibTeX arXiv:2305.11403

Code (2)

fried-rice-lab/emt 공식 구현 pytorch
fried-rice-lab/friedricelab 공식 구현 pytorch

Tasks

Image Super-ResolutionSuper-Resolution

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음
Residual Connection 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

Single Image Super Resolution based on a Modified U-net with Mixed Gradient Loss

2019-11-21 · Zhengyang Lu, Ying Chen

Single image super-resolution (SISR) is the task of inferring a high-resolution image from a single low-resolution image. Recent research on super-resolution has achieved great progress due to the development of deep con…

Image Super-ResolutionSuper-Resolution

Phase-Aligned RoPE for Mixed-Resolution Diffusion Transformer

2025-11-24 · Haoyu Wu, Jingyi Xu, Qiaomu Miao, Dimitris Samaras 외 arxiv

Rotary positional embeddings (RoPE) are widely used in diffusion transformers (DiTs) to encode spatial relationships, yet their behavior with mixed-resolution tokens remains underexplored. A natural approach is to rescal…

Computational Efficiency

Hybrid Transformer and CNN Attention Network for Stereo Image Super-resolution

2023-05-09 · Ming Cheng, Haoyu Ma, Qiufang Ma, Xiaopeng Sun 외

Multi-stage strategies are frequently employed in image restoration tasks. While transformer-based methods have exhibited high efficiency in single-image super-resolution tasks, they have not yet shown significant advant…

Data AugmentationImage EnhancementImage RestorationImage Super-Resolution+2

Vision Transformers with Mixed-Resolution Tokenization

2023-04-01 · Tomer Ronen, Omer Levy, Avram Golbert

Vision Transformer models process input images by dividing them into a spatially regular grid of equal-size patches. Conversely, Transformers were originally introduced over natural language sequences, where each token r…

image-classificationImage Classification

MaxSR: Image Super-Resolution Using Improved MaxViT

2023-07-14 · Bincheng Yang, Gangshan Wu

While transformer models have been demonstrated to be effective for natural language processing tasks and high-level vision tasks, only a few attempts have been made to use powerful transformer models for single image su…

Image Super-ResolutionSuper-Resolution