paper-with-me

홈 › Papers

Paying U-Attention to Textures: Multi-Stage Hourglass Vision Transformer for Universal Texture Synthesis

2022-02-23 · Shouchang Guo, Valentin Deschaintre, Douglas Noll, Arthur Roullier

We present a novel U-Attention vision Transformer for universal texture synthesis. We exploit the natural long-range dependencies enabled by the attention mechanism to allow our approach to synthesize diverse textures while preserving their structures in a single inference. We propose a hierarchical hourglass backbone that attends to the global structure and performs patch mapping at varying scales in a coarse-to-fine-to-coarse stream. Completed by skip connection and convolution designs that propagate and fuse information at different scales, our hierarchical U-Attention architecture unifies attention to features from macro structures to micro details, and progressively refines synthesis results at successive stages. Our method achieves stronger 2$\times$ synthesis than previous work on both stochastic and structured textures while generalizing to unseen textures without fine-tuning. Ablation studies demonstrate the effectiveness of each component of our architecture.

📄 PDF Abstract BibTeX arXiv:2202.11703

Code (0)

등록된 구현이 없습니다.

Tasks

Texture Synthesis

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Adam 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

LAPX: Lightweight Hourglass Network with Global Context

2025-12-18 · Haopeng Zhao, Marsha Mariya Kappan, Mahdi Bamdad, Francisco Cruz arxiv

Human pose estimation is a crucial task in computer vision. Methods that have SOTA (State-of-the-Art) accuracy, often involve a large number of parameters and incur substantial computational cost. Many lightweight varian…

Pose Estimation

Revisiting the Shape Convention of Transformer Language Models

2026-02-06 · Feng-Ting Liao, Meng-Hsi Chen, Guan-Ting Yi, Da-shan Shiu arxiv

The architectural shape of dense Transformers has remained remarkably stable: narrow-wide-narrow feed-forward networks (FFNs) consume most non-embedding parameters. Motivated by theoretical and empirical evidences that r…

Multi-Context Attention for Human Pose Estimation

2017-02-24 · CVPR 2017 7 · Xiao Chu, Wei Yang, Wanli Ouyang, Cheng Ma 외

In this paper, we propose to incorporate convolutional neural networks with a multi-context attention mechanism into an end-to-end framework for human pose estimation. We adopt stacked hourglass networks to generate atte…

Pose Estimation

Attention-Enhanced Lightweight Hourglass Network for Human Pose Estimation

2024-12-09 · Marsha Mariya Kappan, Eduardo Benitez Sandoval, Erik Meijering, Francisco Cruz

Pose estimation is a critical task in computer vision with a wide range of applications from activity monitoring to human-robot interaction. However,most of the existing methods are computationally expensive or have comp…

Pose Estimation

Multi-Scale Stacked Hourglass Network for Human Pose Estimation

2019-05-01 · ICLR 2019 5 · Chunsheng Guo, Wenlong Du, Na Ying

Stacked hourglass network has become an important model for Human pose estimation. The estimation of human body posture depends on the global information of the keypoints type and the local information of the keypoints l…

Pose Estimation