Multiscale texture separation

• URL: http://arxiv.org/abs/2411.00894v1
• Date: Fri, 01 Nov 2024 00:33:36 GMT
• Title: Multiscale texture separation
• Authors: Jerome Gilles,
• Abstract summary: We investigate theoretically the behavior of Meyer's image cartoon + texture decomposition model. By combining the decomposition model and a well chosen Littlewood-Paley filter, it is possible to extract almost perfectly a certain class of textures.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: In this paper, we investigate theoretically the behavior of Meyer's image cartoon + texture decomposition model. Our main results is a new theorem which shows that, by combining the decomposition model and a well chosen Littlewood-Paley filter, it is possible to extract almost perfectly a certain class of textures. This theorem leads us to the construction of a parameterless multiscale texture separation algorithm. Finally, we propose to extend this algorithm into a directional multiscale texture separation algorithm by designing a directional Littlewood-Paley filter bank. Several experiments show the efficiency of the proposed method both on synthetic and real images.

Related papers

• CasTex: Cascaded Text-to-Texture Synthesis via Explicit Texture Maps and Physically-Based Shading [7.851991808404223]
  We aim to achieve realistic model appearances under varying lighting conditions. In our setup, score distillation sampling yields high-quality textures out-of-the box.
  arXiv  Detail & Related papers  (2025-04-09T13:08:30Z)
• Empirical curvelet based Fully Convolutional Network for supervised texture image segmentation [2.780132626494265]
  We propose a new approach to perform supervised texture classification/segmentation. The proposed idea is to feed a Fully Convolutional Network with specific texture descriptors. Our approach is evaluated on several datasets and compare the results to various state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2024-10-28T21:49:40Z)
• Infinite Texture: Text-guided High Resolution Diffusion Texture Synthesis [61.189479577198846]
  We present Infinite Texture, a method for generating arbitrarily large texture images from a text prompt. Our approach fine-tunes a diffusion model on a single texture, and learns to embed that statistical distribution in the output domain of the model. At generation time, our fine-tuned diffusion model is used through a score aggregation strategy to generate output texture images of arbitrary resolution on a single GPU.
  arXiv  Detail & Related papers  (2024-05-13T21:53:09Z)
• Semi-sparsity Priors for Image Structure Analysis and Extraction [3.130722489512822]
  We propose a semi-sparse regularization framework for image structural analysis and extraction. We show that it is capable of preserving image structures without introducing notorious staircase artifacts. We also introduce an efficient numerical solution based on an direction method of multipliers (ADMM) algorithm.
  arXiv  Detail & Related papers  (2023-08-17T18:22:00Z)
• Pyramid Texture Filtering [86.15126028139736]
  We present a simple but effective technique to smooth out textures while preserving the prominent structures. Our method is built upon a key observation -- the coarsest level in a Gaussian pyramid often naturally eliminates textures and summarizes the main image structures. We show that our approach is effective to separate structure from texture of different scales, local contrasts, and forms, without degrading structures or introducing visual artifacts.
  arXiv  Detail & Related papers  (2023-05-11T02:05:30Z)
• Metropolis Theorem and Its Applications in Single Image Detail Enhancement [10.213517608227686]
  Our method is different, and its innovation lies in the special way to get the image detail layer. Due to the diversity of image texture features, perfect matching is often not possible. Our algorithm can achieve better results in quantitative metrics testing and visual effects evaluation.
  arXiv  Detail & Related papers  (2023-02-20T05:00:20Z)
• SeamlessGAN: Self-Supervised Synthesis of Tileable Texture Maps [3.504542161036043]
  We present SeamlessGAN, a method capable of automatically generating tileable texture maps from a single input exemplar. In contrast to most existing methods, focused solely on solving the synthesis problem, our work tackles both problems, synthesis and tileability, simultaneously.
  arXiv  Detail & Related papers  (2022-01-13T18:24:26Z)
• Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition [62.41259783906452]
  We present a novel global compression framework for deep neural networks. It automatically analyzes each layer to identify the optimal per-layer compression ratio. Our results open up new avenues for future research into the global performance-size trade-offs of modern neural networks.
  arXiv  Detail & Related papers  (2021-07-23T20:01:30Z)
• Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE [74.29384873537587]
  We propose a two-stage model for diverse inpainting, where the first stage generates multiple coarse results each of which has a different structure, and the second stage refines each coarse result separately by augmenting texture. Experimental results on CelebA-HQ, Places2, and ImageNet datasets show that our method not only enhances the diversity of the inpainting solutions but also improves the visual quality of the generated multiple images.
  arXiv  Detail & Related papers  (2021-03-18T05:10:49Z)
• Contour Integration using Graph-Cut and Non-Classical Receptive Field [4.935491924643742]
  We propose a novel method to detect image contours from the extracted edge segments of other algorithms. The proposed energy functions are inspired by the surround modulation in the primary visual cortex that help suppressing texture noise.
  arXiv  Detail & Related papers  (2020-10-27T19:07:13Z)
• Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression [145.04742985050808]
  We analyze two popular network compression techniques, i.e. filter pruning and low-rank decomposition, in a unified sense. By changing the way the sparsity regularization is enforced, filter pruning and low-rank decomposition can be derived accordingly. Our approach proves its potential as it compares favorably to the state-of-the-art on several benchmarks.
  arXiv  Detail & Related papers  (2020-03-19T17:57:26Z)
• Image Matching across Wide Baselines: From Paper to Practice [80.9424750998559]
  We introduce a comprehensive benchmark for local features and robust estimation algorithms. Our pipeline's modular structure allows easy integration, configuration, and combination of different methods. We show that with proper settings, classical solutions may still outperform the perceived state of the art.
  arXiv  Detail & Related papers  (2020-03-03T15:20:57Z)

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.