S-INF: Towards Realistic Indoor Scene Synthesis via Scene Implicit Neural Field

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liang, Zixi, Xu, Guowei, Wu, Haifeng, Huang, Ye, Li, Wen, Duan, Lixin
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912176661331968
author Liang, Zixi
Xu, Guowei
Wu, Haifeng
Huang, Ye
Li, Wen
Duan, Lixin
author_facet Liang, Zixi
Xu, Guowei
Wu, Haifeng
Huang, Ye
Li, Wen
Duan, Lixin
contents Learning-based methods have become increasingly popular in 3D indoor scene synthesis (ISS), showing superior performance over traditional optimization-based approaches. These learning-based methods typically model distributions on simple yet explicit scene representations using generative models. However, due to the oversimplified explicit representations that overlook detailed information and the lack of guidance from multimodal relationships within the scene, most learning-based methods struggle to generate indoor scenes with realistic object arrangements and styles. In this paper, we introduce a new method, Scene Implicit Neural Field (S-INF), for indoor scene synthesis, aiming to learn meaningful representations of multimodal relationships, to enhance the realism of indoor scene synthesis. S-INF assumes that the scene layout is often related to the object-detailed information. It disentangles the multimodal relationships into scene layout relationships and detailed object relationships, fusing them later through implicit neural fields (INFs). By learning specialized scene layout relationships and projecting them into S-INF, we achieve a realistic generation of scene layout. Additionally, S-INF captures dense and detailed object relationships through differentiable rendering, ensuring stylistic consistency across objects. Through extensive experiments on the benchmark 3D-FRONT dataset, we demonstrate that our method consistently achieves state-of-the-art performance under different types of ISS.
format Preprint
id arxiv_https___arxiv_org_abs_2412_17561
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle S-INF: Towards Realistic Indoor Scene Synthesis via Scene Implicit Neural Field
Liang, Zixi
Xu, Guowei
Wu, Haifeng
Huang, Ye
Li, Wen
Duan, Lixin
Computer Vision and Pattern Recognition
Learning-based methods have become increasingly popular in 3D indoor scene synthesis (ISS), showing superior performance over traditional optimization-based approaches. These learning-based methods typically model distributions on simple yet explicit scene representations using generative models. However, due to the oversimplified explicit representations that overlook detailed information and the lack of guidance from multimodal relationships within the scene, most learning-based methods struggle to generate indoor scenes with realistic object arrangements and styles. In this paper, we introduce a new method, Scene Implicit Neural Field (S-INF), for indoor scene synthesis, aiming to learn meaningful representations of multimodal relationships, to enhance the realism of indoor scene synthesis. S-INF assumes that the scene layout is often related to the object-detailed information. It disentangles the multimodal relationships into scene layout relationships and detailed object relationships, fusing them later through implicit neural fields (INFs). By learning specialized scene layout relationships and projecting them into S-INF, we achieve a realistic generation of scene layout. Additionally, S-INF captures dense and detailed object relationships through differentiable rendering, ensuring stylistic consistency across objects. Through extensive experiments on the benchmark 3D-FRONT dataset, we demonstrate that our method consistently achieves state-of-the-art performance under different types of ISS.
title S-INF: Towards Realistic Indoor Scene Synthesis via Scene Implicit Neural Field
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.17561