Alert button
Picture for Pengqian Yu

Pengqian Yu

Alert button

Hierarchical Reinforcement Learning for Furniture Layout in Virtual Indoor Scenes

Oct 19, 2022
Xinhan Di, Pengqian Yu

Figure 1 for Hierarchical Reinforcement Learning for Furniture Layout in Virtual Indoor Scenes
Figure 2 for Hierarchical Reinforcement Learning for Furniture Layout in Virtual Indoor Scenes
Figure 3 for Hierarchical Reinforcement Learning for Furniture Layout in Virtual Indoor Scenes
Figure 4 for Hierarchical Reinforcement Learning for Furniture Layout in Virtual Indoor Scenes

In real life, the decoration of 3D indoor scenes through designing furniture layout provides a rich experience for people. In this paper, we explore the furniture layout task as a Markov decision process (MDP) in virtual reality, which is solved by hierarchical reinforcement learning (HRL). The goal is to produce a proper two-furniture layout in the virtual reality of the indoor scenes. In particular, we first design a simulation environment and introduce the HRL formulation for a two-furniture layout. We then apply a hierarchical actor-critic algorithm with curriculum learning to solve the MDP. We conduct our experiments on a large-scale real-world interior layout dataset that contains industrial designs from professional designers. Our numerical results demonstrate that the proposed model yields higher-quality layouts as compared with the state-of-art models.

* Accepted by Reinforcement Learning for Real Life Workshop @ NeurIPS 2022 
Viaarxiv icon

LWA-HAND: Lightweight Attention Hand for Interacting Hand Reconstruction

Aug 27, 2022
Xinhan Di, Pengqian Yu

Figure 1 for LWA-HAND: Lightweight Attention Hand for Interacting Hand Reconstruction
Figure 2 for LWA-HAND: Lightweight Attention Hand for Interacting Hand Reconstruction
Figure 3 for LWA-HAND: Lightweight Attention Hand for Interacting Hand Reconstruction
Figure 4 for LWA-HAND: Lightweight Attention Hand for Interacting Hand Reconstruction

Recent years have witnessed great success for hand reconstruction in real-time applications such as visual reality and augmented reality while interacting with two-hand reconstruction through efficient transformers is left unexplored. In this paper, we propose a method called lightweight attention hand (LWA-HAND) to reconstruct hands in low flops from a single RGB image. To solve the occlusion and interaction problem in efficient attention architectures, we propose three mobile attention modules in this paper. The first module is a lightweight feature attention module that extracts both local occlusion representation and global image patch representation in a coarse-to-fine manner. The second module is a cross image and graph bridge module which fuses image context and hand vertex. The third module is a lightweight cross-attention mechanism that uses element-wise operation for the cross-attention of two hands in linear complexity. The resulting model achieves comparable performance on the InterHand2.6M benchmark in comparison with the state-of-the-art models. Simultaneously, it reduces the flops to $0.47GFlops$ while the state-of-the-art models have heavy computations between $10GFlops$ and $20GFlops$.

* Accepted by ECCV 2022 Computer Vision for Metaverse Workshop (16 pages, 6 figures, 1 table) 
Viaarxiv icon

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

Feb 18, 2021
Xinhan Di, Pengqian Yu

Figure 1 for Multi-Agent Reinforcement Learning of 3D Furniture Layout Simulation in Indoor Graphics Scenes
Figure 2 for Multi-Agent Reinforcement Learning of 3D Furniture Layout Simulation in Indoor Graphics Scenes
Figure 3 for Multi-Agent Reinforcement Learning of 3D Furniture Layout Simulation in Indoor Graphics Scenes
Figure 4 for Multi-Agent Reinforcement Learning of 3D Furniture Layout Simulation in Indoor Graphics Scenes

In the industrial interior design process, professional designers plan the furniture layout to achieve a satisfactory 3D design for selling. In this paper, we explore the interior graphics scenes design task as a Markov decision process (MDP) in 3D simulation, which is solved by multi-agent reinforcement learning. The goal is to produce furniture layout in the 3D simulation of the indoor graphics scenes. In particular, we firstly transform the 3D interior graphic scenes into two 2D simulated scenes. We then design the simulated environment and apply two reinforcement learning agents to learn the optimal 3D layout for the MDP formulation in a cooperative way. We conduct our experiments on a large-scale real-world interior layout dataset that contains industrial designs from professional designers. Our numerical results demonstrate that the proposed model yields higher-quality layouts as compared with the state-of-art model. The developed simulator and codes are available at \url{https://github.com/CODE-SUBMIT/simulator2}.

* 8 pages, 3 figures submit to conference. arXiv admin note: substantial text overlap with arXiv:2101.07462 
Viaarxiv icon

Deep Reinforcement Learning for Producing Furniture Layout in Indoor Scenes

Jan 19, 2021
Xinhan Di, Pengqian Yu

Figure 1 for Deep Reinforcement Learning for Producing Furniture Layout in Indoor Scenes
Figure 2 for Deep Reinforcement Learning for Producing Furniture Layout in Indoor Scenes
Figure 3 for Deep Reinforcement Learning for Producing Furniture Layout in Indoor Scenes
Figure 4 for Deep Reinforcement Learning for Producing Furniture Layout in Indoor Scenes

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. In this paper, we explore the interior scene design task as a Markov decision process (MDP), which is solved by deep reinforcement learning. The goal is to produce an accurate position and size of the furniture simultaneously for the indoor layout task. In particular, we first formulate the furniture layout task as a MDP problem by defining the state, action, and reward function. We then design the simulated environment and train reinforcement learning agents to produce the optimal layout for the MDP formulation. We conduct our experiments on a large-scale real-world interior layout dataset that contains industrial designs from professional designers. Our numerical results demonstrate that the proposed model yields higher-quality layouts as compared with the state-of-art model. The developed simulator and codes are available at \url{https://github.com/CODE-SUBMIT/simulator1}.

* computer vision reinforcement learning. arXiv admin note: text overlap with arXiv:2012.08514, arXiv:2012.08131 
Viaarxiv icon

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

Dec 15, 2020
Xinhan Di, Pengqian Yu, Danfeng Yang, Hong Zhu, Changyu Sun, YinDong Liu

Figure 1 for End-to-end Generative Floor-plan and Layout with Attributes and Relation Graph
Figure 2 for End-to-end Generative Floor-plan and Layout with Attributes and Relation Graph
Figure 3 for End-to-end Generative Floor-plan and Layout with Attributes and Relation Graph
Figure 4 for End-to-end Generative Floor-plan and Layout with Attributes and Relation Graph

In this paper, we propose an end-end model for producing furniture layout for interior scene synthesis from the random vector. This proposed model is aimed to support professional interior designers to produce the interior decoration solutions more quickly. The proposed model combines a conditional floor-plan module of the room, a conditional graphical floor-plan module of the room and a conditional layout module. As compared with the prior work on scene synthesis, our proposed three modules enhance the ability of auto-layout generation given the dimensional category of the room. We conduct our experiments on the proposed real-world interior layout dataset that contains $191208$ designs from the professional designers. Our numerical results demonstrate that the proposed model yields higher-quality layouts in comparison with the state-of-the-art model. The dataset and code are released \href{https://github.com/CODE-SUBMIT/dataset3}{Dataset,Code}

* Submitted to CV Conference. arXiv admin note: text overlap with arXiv:2006.13527. text overlap with arXiv:2012.08131 
Viaarxiv icon

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

Dec 15, 2020
Xinhan Di, Pengqian Yu, Danfeng Yang, Hong Zhu, Changyu Sun, YinDong Liu

Figure 1 for Deep Layout of Custom-size Furniture through Multiple-domain Learning
Figure 2 for Deep Layout of Custom-size Furniture through Multiple-domain Learning
Figure 3 for Deep Layout of Custom-size Furniture through Multiple-domain Learning
Figure 4 for Deep Layout of Custom-size Furniture through Multiple-domain Learning

In this paper, we propose a multiple-domain model for producing a custom-size furniture layout in the interior scene. This model is aimed to support professional interior designers to produce interior decoration solutions with custom-size furniture more quickly. The proposed model combines a deep layout module, a domain attention module, a dimensional domain transfer module, and a custom-size module in the end-end training. Compared with the prior work on scene synthesis, our proposed model enhances the ability of auto-layout of custom-size furniture in the interior room. We conduct our experiments on a real-world interior layout dataset that contains $710,700$ designs from professional designers. Our numerical results demonstrate that the proposed model yields higher-quality layouts of custom-size furniture in comparison with the state-of-art model.

* Submitted to CV Conference. arXiv admin note: text overlap with arXiv:2006.13527 
Viaarxiv icon

Fed+: A Family of Fusion Algorithms for Federated Learning

Sep 14, 2020
Pengqian Yu, Laura Wynter, Shiau Hong Lim

Figure 1 for Fed+: A Family of Fusion Algorithms for Federated Learning
Figure 2 for Fed+: A Family of Fusion Algorithms for Federated Learning
Figure 3 for Fed+: A Family of Fusion Algorithms for Federated Learning
Figure 4 for Fed+: A Family of Fusion Algorithms for Federated Learning

We present a class of methods for federated learning, which we call Fed+, pronounced FedPlus. The class of methods encompasses and unifies a number of recent algorithms proposed for federated learning and permits easily defining many new algorithms. The principal advantage of this class of methods is to better accommodate the real-world characteristics found in federated learning training, such as the lack of IID data across the parties in the federation. We demonstrate the use and benefits of this class of algorithms on standard benchmark datasets and a challenging real-world problem where catastrophic failure has a serious impact, namely in financial portfolio management.

Viaarxiv icon

Structural Plan of Indoor Scenes with Personalized Preferences

Aug 05, 2020
Xinhan Di, Pengqian Yu, Hong Zhu, Lei Cai, Qiuyan Sheng, Changyu Sun

Figure 1 for Structural Plan of Indoor Scenes with Personalized Preferences
Figure 2 for Structural Plan of Indoor Scenes with Personalized Preferences
Figure 3 for Structural Plan of Indoor Scenes with Personalized Preferences
Figure 4 for Structural Plan of Indoor Scenes with Personalized Preferences

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. The proposed model is able to automatically produce the layout of objects of a particular indoor scene according to property owners' preferences. In particular, the model consists of the extraction of abstract graph, conditional graph generation, and conditional scene instantiation. We provide an interior layout dataset that contains real-world 11000 designs from professional designers. Our numerical results on the dataset demonstrate the effectiveness of the proposed model compared with the state-of-art methods.

* Accepted by the 8th International Workshop on Assistive Computer Vision and Robotics (ACVR) in Conjunction with ECCV 2020 
Viaarxiv icon

Adversarial Model for Rotated Indoor Scenes Planning

Jul 07, 2020
Xinhan Di, Pengqian Yu, Hong Zhu, Lei Cai, Qiuyan Sheng, Changyu Sun

Figure 1 for Adversarial Model for Rotated Indoor Scenes Planning
Figure 2 for Adversarial Model for Rotated Indoor Scenes Planning
Figure 3 for Adversarial Model for Rotated Indoor Scenes Planning
Figure 4 for Adversarial Model for Rotated Indoor Scenes Planning

In this paper, we propose an adversarial model for producing furniture layout for interior scene synthesis when the interior room is rotated. The proposed model combines a conditional adversarial network, a rotation module, a mode module, and a rotation discriminator module. As compared with the prior work on scene synthesis, our proposed three modules enhance the ability of auto-layout generation and reduce the mode collapse during the rotation of the interior room. We conduct our experiments on a proposed real-world interior layout dataset that contains 14400 designs from the professional designers. Our numerical results demonstrate that the proposed model yields higher-quality layouts for four types of rooms, including the bedroom, the bathroom, the study room, and the tatami room.

Viaarxiv icon