arXiv 2412.175612025-01-04cs.CV

S-INF：通过场景隐式神经场实现逼真的室内场景合成

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

Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China（电子科技大学深圳高等研究院）；School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）；Sichuan Academy of Medical Sciences and Sichuan Provincial People’s Hospital（四川省医学科学院·四川省人民医院）

Zixi Liang, Guowei Xu, Haifeng Wu, Ye Huang, Wen Li, Lixin Duan

备注：: Accepted to AAAI 2025

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出S-INF，通过隐式神经场解耦并融合场景布局与细粒度物体关系，结合可微渲染保证风格一致，在3D-FRONT上实现逼真室内场景合成。

摘要：

基于学习的方法在3D室内场景合成（ISS）中变得越来越流行，并表现出优于传统基于优化方法的性能。这些基于学习的方法通常使用生成模型，在简单但显式的场景表示上建模分布。然而，由于过度简化的显式表示忽略了细节信息，并且缺乏场景内部多模态关系的引导，大多数基于学习的方法难以生成具有逼真物体布局和风格的室内场景。本文提出一种用于室内场景合成的新方法——Scene Implicit Neural Field（S-INF，场景隐式神经场），旨在学习有意义的多模态关系表示，以增强室内场景合成的真实感。S-INF假设场景布局通常与物体细节信息相关。它将多模态关系解耦为场景布局关系和细粒度物体关系，随后通过隐式神经场（INFs）将其融合。通过学习专门的场景布局关系并将其投影到S-INF中，我们实现了逼真的场景布局生成。此外，S-INF通过可微渲染捕获密集且细粒度的物体关系，确保物体之间的风格一致性。在基准3D-FRONT数据集上的大量实验表明，我们的方法在不同类型的ISS下持续取得最先进性能。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。