arXiv subjects

Changyu Sun

Publications and source records attributed to Changyu Sun.

5 recordsLinked to original sources

arXiv2026

From Radiotherapy Dataset to Cherenkov Dose Map: A Digital Linac Monte Carlo Simulation Pipeline

Background: Cherenkov-based radiotherapy monitoring depends on the relationship between dose and locally generated Cherenkov photons, before optical transport and detection. Purpose: To develop a DICOM RT-driven Geant4 digital linac Monte Carlo framework that scores dose and Cherenkov creation together and to evaluate their spatial correspondence. Methods: The framework converts DICOM CT, structure, plan, and dose objects into beam-delivery states and scores energy deposition and Cherenkov photon creation on a common 2.5-mm isotropic grid in a water-equivalent phantom. Static fields, different beam qualities, and a two-arc VMAT plan were tested. Monte Carlo dose was compared with TPS RTDOSE from Acuros XB and AAA; dose-Cherenkov associations and spatial agreement were assessed at voxel, plane, and profile levels. Results: Full-volume 3D dose gamma passing rates (3%/3 mm, 10% threshold) were 97.05%-98.86% for Acuros XB-referenced field-size and beam-quality cases (97.47% with AAA) and 97.84% for VMAT. Cherenkov creation correlated strongly with dose, with voxel $r^2 \geq 0.9890$ and projection/profile $r^2 \geq 0.9942$ in all cases. Dose-Cherenkov 3D gamma passing rates were 97.97%-99.16% for $10\times10$ 6X, 10X, and 15X fields and 96.59% for VMAT, but fell to 71.22% for $5\times5$ fields and 32.82% for 6FFF. Deviations were most apparent near small-field edges and along depth for 6FFF. Conclusions: In a homogeneous water phantom, local Cherenkov creation broadly tracks local dose but shows systematic differences at beam edges and with FFF beam quality. This framework supports future studies of optical transport and surface-based Cherenkov dosimetry.

physics.med-ph↗

arXiv2020

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.

cs.CV↗

arXiv2020

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}

cs.CV↗

arXiv2020

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.

cs.CV↗

arXiv2020

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.

cs.CV↗