paper-with-me

홈 › Papers

Conv-MPN: Convolutional Message Passing Neural Network for Structured Outdoor Architecture Reconstruction

2019-12-04 · CVPR 2020 6 · Fuyang Zhang, Nelson Nauata, Yasutaka Furukawa

This paper proposes a novel message passing neural (MPN) architecture Conv-MPN, which reconstructs an outdoor building as a planar graph from a single RGB image. Conv-MPN is specifically designed for cases where nodes of a graph have explicit spatial embedding. In our problem, nodes correspond to building edges in an image. Conv-MPN is different from MPN in that 1) the feature associated with a node is represented as a feature volume instead of a 1D vector; and 2) convolutions encode messages instead of fully connected layers. Conv-MPN learns to select a true subset of nodes (i.e., building edges) to reconstruct a building planar graph. Our qualitative and quantitative evaluations over 2,000 buildings show that Conv-MPN makes significant improvements over the existing fully neural solutions. We believe that the paper has a potential to open a new line of graph neural network research for structured geometry reconstruction.

📄 PDF Abstract BibTeX arXiv:1912.01756

Code (1)

zhangfuyang/Conv-MPN 공식 구현 pytorch

Tasks

Graph Neural Network

Methods 이 논문이 사용한 방법론

Graph Neural Network 설명 없음
MPN 설명 없음

Similar Papers 제목 키워드 기반

Deeply Learning the Messages in Message Passing Inference

2015-06-06 · NeurIPS 2015 12 · Guosheng Lin, Chunhua Shen, Ian Reid, Anton Van Den Hengel

Deep structured output learning shows great promise in tasks like semantic image segmentation. We proffer a new, efficient deep structured model learning scheme, in which we show how deep Convolutional Neural Networks (C…

Image SegmentationSemantic SegmentationStructured Prediction

Convergence of Message Passing Graph Neural Networks with Generic Aggregation On Large Random Graphs

2023-04-21 · Matthieu Cordonnier, Nicolas Keriven, Nicolas Tremblay, Samuel Vaiter

We study the convergence of message passing graph neural networks on random graph models to their continuous counterpart as the number of nodes tends to infinity. Until now, this convergence was only known for architectu…

CRF-CNN: Modeling Structured Information in Human Pose Estimation

2016-11-02 · NeurIPS 2016 12 · Xiao Chu, Wanli Ouyang, Hongsheng Li, Xiaogang Wang

Deep convolutional neural networks (CNN) have achieved great success. On the other hand, modeling structural information has been proved critical in many vision problems. It is of great interest to integrate them effecti…

Pose Estimation

Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object Detection

2019-09-10 · ICCV 2019 10 · Yingyue Xu, Dan Xu, Xiaopeng Hong, Wanli Ouyang 외

Recent saliency models extensively explore to incorporate multi-scale contextual information from Convolutional Neural Networks (CNNs). Besides direct fusion strategies, many approaches introduce message-passing to enhan…

object-detectionObject DetectionPredictionRGB Salient Object Detection+1

Schema-Aware Deep Graph Convolutional Networks for Heterogeneous Graphs

2021-05-03 · Saurav Manchanda, Da Zheng, George Karypis

Graph convolutional network (GCN) based approaches have achieved significant progress for solving complex, graph-structured problems. GCNs incorporate the graph structure information and the node (or edge) features throu…