Search Results for author: Xinhan Di

Found 13 papers, 6 papers with code

Multi-Agent Reinforcement Learning of 3D Furniture Layout Simulation in Indoor Graphics Scenes

1 code implementation18 Feb 2021 Xinhan Di, Pengqian Yu

In the industrial interior design process, professional designers plan the furniture layout to achieve a satisfactory 3D design for selling.

Multi-agent Reinforcement Learning reinforcement-learning

Deep Reinforcement Learning for Producing Furniture Layout in Indoor Scenes

1 code implementation19 Jan 2021 Xinhan Di, Pengqian Yu

In the industrial interior design process, professional designers plan the size and position of furniture in a room to achieve a satisfactory design for selling.

reinforcement-learning

End-to-end Generative Floor-plan and Layout with Attributes and Relation Graph

1 code implementation15 Dec 2020 Xinhan Di, Pengqian Yu, Danfeng Yang, Hong Zhu, Changyu Sun, YinDong Liu

We conduct our experiments on the proposed real-world interior layout dataset that contains $191208$ designs from the professional designers.

Deep Layout of Custom-size Furniture through Multiple-domain Learning

no code implementations15 Dec 2020 Xinhan Di, Pengqian Yu, Danfeng Yang, Hong Zhu, Changyu Sun, YinDong Liu

In this paper, we propose a multiple-domain model for producing a custom-size furniture layout in the interior scene.

Structural Plan of Indoor Scenes with Personalized Preferences

no code implementations4 Aug 2020 Xinhan Di, Pengqian Yu, Hong Zhu, Lei Cai, Qiuyan Sheng, Changyu Sun

In this paper, we propose an assistive model that supports professional interior designers to produce industrial interior decoration solutions and to meet the personalized preferences of the property owners.

Graph Generation

Adversarial Model for Rotated Indoor Scenes Planning

no code implementations24 Jun 2020 Xinhan Di, Pengqian Yu, Hong Zhu, Lei Cai, Qiuyan Sheng, Changyu Sun

In this paper, we propose an adversarial model for producing furniture layout for interior scene synthesis when the interior room is rotated.

The Direction-Aware, Learnable, Additive Kernels and the Adversarial Network for Deep Floor Plan Recognition

no code implementations30 Jan 2020 Yuli Zhang, Yeyang He, Shaowen Zhu, Xinhan Di

Besides, an adversarial network with two discriminators is proposed to further improve the accuracy of the elements and to reduce the noise of the semantic segmentation.

Semantic Segmentation

Mutual Information Maximization in Graph Neural Networks

2 code implementations21 May 2019 Xinhan Di, Pengqian Yu, Rui Bu, Mingchao Sun

In order to reduce the loss, we extend the GNNs frameworks by exploring the aggregation and iteration scheme in the methodology of mutual information.

General Classification Graph Classification +2

Ambient Hidden Space of Generative Adversarial Networks

no code implementations2 Jul 2018 Xinhan Di, Pengqian Yu, Meng Tian

In this paper, we extend the ambient module to the hidden space of the generator, and provide the uniqueness condition and the corresponding strategy for the ambient hidden generator in the adversarial training process.

Towards Adversarial Training with Moderate Performance Improvement for Neural Network Classification

no code implementations1 Jul 2018 Xinhan Di, Pengqian Yu, Meng Tian

It has been demonstrated that deep neural networks are prone to noisy examples particular adversarial samples during inference process.

General Classification

PointCNN: Convolution On $\mathcal{X}$-Transformed Points

12 code implementations NeurIPS 2018 Yangyan Li, Rui Bu, Mingchao Sun, Wei Wu, Xinhan Di, Baoquan Chen

The proposed method is a generalization of typical CNNs to feature learning from point clouds, thus we call it PointCNN.

 Ranked #1 on 3D Instance Segmentation on S3DIS (mIoU metric)

3D Instance Segmentation 3D Part Segmentation +1

3D Reconstruction of Simple Objects from A Single View Silhouette Image

no code implementations17 Jan 2017 Xinhan Di, Pengqian Yu

While recent deep neural networks have achieved promising results for 3D reconstruction from a single-view image, these rely on the availability of RGB textures in images and extra information as supervision.

3D Reconstruction

Cannot find the paper you are looking for? You can Submit a new open access paper.