paper-with-me

Papers

Generating Non-Stationary Textures using Self-Rectification

2024-01-05 · CVPR 2024 1 · Yang Zhou, Rongjun Xiao, Dani Lischinski, Daniel Cohen-Or, Hui Huang

This paper addresses the challenge of example-based non-stationary texture synthesis. We introduce a novel twostep approach wherein users first modify a reference texture using standard image editing tools, yielding an initial rough target for the synthesis. Subsequently, our proposed method, termed "self-rectification", automatically refines this target into a coherent, seamless texture, while faithfully preserving the distinct visual characteristics of the reference exemplar. Our method leverages a pre-trained diffusion network, and uses self-attention mechanisms, to gradually align the synthesized texture with the reference, ensuring the retention of the structures in the provided target. Through experimental validation, our approach exhibits exceptional proficiency in handling non-stationary textures, demonstrating significant advancements in texture synthesis when compared to existing state-of-the-art techniques. Code is available at https://github.com/xiaorongjun000/Self-Rectification

📄 PDF Abstract BibTeX arXiv:2401.02847

Code (1)

xiaorongjun000/self-rectification 공식 구현 pytorch

Tasks

Texture Synthesis

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Stochastic Super-Resolution For Gaussian Textures

2023-03-03 · Emile Pierret, Bruno Galerne

Super-resolution (SR) is an ill-posed inverse problem which consists in proposing high-resolution images consistent with a given low-resolution one. While most SR algorithms are deterministic, stochastic SR deals with de…

Super-Resolution

Non-Stationary Texture Synthesis by Adversarial Expansion

2018-05-11 · Yang Zhou, Zhen Zhu, Xiang Bai, Dani Lischinski 외

The real world exhibits an abundance of non-stationary textures. Examples include textures with large-scale structures, as well as spatially variant and inhomogeneous textures. While existing example-based texture synthe…

Generative Adversarial NetworkTexture Synthesis

Diffusion-based Holistic Texture Rectification and Synthesis

2023-09-26 · Guoqing Hao, Satoshi Iizuka, Kensho Hara, Edgar Simo-Serra 외

We present a novel framework for rectifying occlusions and distortions in degraded texture samples from natural images. Traditional texture synthesis approaches focus on generating textures from pristine samples, which n…

Texture Synthesis

Adaptive Rectification Sampling for Test-Time Compute Scaling

2025-04-02 · Zhendong Tan, Xingjun Zhang, Chaoyi Hu, Yancheng Pan 외

The newly released OpenAI-o1 and DeepSeek-R1 have demonstrated that test-time scaling can significantly improve model performance, especially in complex tasks such as logical reasoning. Common test-time scaling methods i…

GSM8KLogical Reasoning

Learning in a Single Domain for Non-Stationary Multi-Texture Synthesis

2023-05-10 · Xudong Xie, Zhen Zhu, Zijie Wu, Zhiliang Xu 외

This paper aims for a new generation task: non-stationary multi-texture synthesis, which unifies synthesizing multiple non-stationary textures in a single model. Most non-stationary textures have large scale variance and…

Texture Synthesis