paper-with-me

Papers

Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis

2016-01-18 · CVPR 2016 6 · Chuan Li, Michael Wand

This paper studies a combination of generative Markov random field (MRF) models and discriminatively trained deep convolutional neural networks (dCNNs) for synthesizing 2D images. The generative MRF acts on higher-levels of a dCNN feature pyramid, controling the image layout at an abstract level. We apply the method to both photographic and non-photo-realistic (artwork) synthesis tasks. The MRF regularizer prevents over-excitation artifacts and reduces implausible feature mixtures common to previous dCNN inversion approaches, permitting synthezing photographic content with increased visual plausibility. Unlike standard MRF-based texture synthesis, the combined system can both match and adapt local features with considerable variability, yielding results far out of reach of classic generative MRF methods.

📄 PDF Abstract BibTeX arXiv:1601.04589

Code (7)

chuanli11/CNNMRF 공식 구현 torch
DmitryUlyanov/fast-neural-doodle torch
Garfield35/Doodle tf
alexjc/neural-doodle
awentzonline/image-analogies tf
factoryIO/1-simple_neural_style_transfer tf
paulwarkentin/pytorch-neural-doodle pytorch

Tasks

Image GenerationTexture Synthesis

Methods 이 논문이 사용한 방법론

DCNN Diffusion-convolutional neural networks (DCNN) is a model for graph-structured data. Through the introduction of a diffusion-convolution operation, diffusion-based representations…

Similar Papers 제목 키워드 기반

Urban Zoning Using Higher-Order Markov Random Fields on Multi-View Imagery Data

2018-09-01 · ECCV 2018 9 · Tian Feng, Quang-Trung Truong, Duc Thanh Nguyen, Jing Yu Koh 외

Urban zoning enables various applications in land use analysis and urban planning. As cities evolve, it is important to constantly update the zoning maps of cities to reflect urban pattern changes. This paper proposes a …

Unsupervised Segmentation of Micro-CT Scans of Polyurethane Structures By Combining Hidden-Markov-Random Fields and a U-Net

2025-11-14 · Julian Grolig, Lars Griem, Michael Selzer, Hans-Ulrich Kauczor 외 arxiv

Extracting digital material representations from images is a necessary prerequisite for a quantitative analysis of material properties. Different segmentation approaches have been extensively studied in the past to achie…

Image Labeling with Markov Random Fields and Conditional Random Fields

2018-11-28 · Shangxuan Wu, Xinshuo Weng

Most existing methods for object segmentation in computer vision are formulated as a labeling task. This, in general, could be transferred to a pixel-wise label assignment task, which is quite similar to the structure of…

SegmentationSemantic Segmentation

Probabilistic Inference of Binary Markov Random Fields in Spiking Neural Networks through Mean-field Approximation

2019-02-22 · Yajing Zheng, Shanshan Jia, Zhaofei Yu, Tiejun Huang 외

Recent studies have suggested that the cognitive process of the human brain is realized as probabilistic inference and can be further modeled by probabilistic graphical models like Markov random fields. Nevertheless, it …

DenoisingImage Denoisingvalid

Efficient methods for Gaussian Markov random fields under sparse linear constraints

2021-06-03 · NeurIPS 2021 12 · David Bolin, Jonas Wallin

Methods for inference and simulation of linearly constrained Gaussian Markov Random Fields (GMRF) are computationally prohibitive when the number of constraints is large. In some cases, such as for intrinsic GMRFs, they …