arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.00670cs.CVcs.LG
收藏

基于局部辐射场的无约束场景生成

Unconstrained Scene Generation with Locally Conditioned Radiance Fields

Apple(苹果公司);University of Guelph(圭尔夫大学);Vector Institute(向量研究所)

Terrance DeVries, Miguel Angel Bautista, Nitish Srivastava, Graham W. Taylor, Joshua M. Susskind

摘要:

我们解决了在复杂、逼真的室内场景中学习分布的挑战。在本文中,我们介绍了生成场景网络(GSN),它学习分解场景到一个集合的许多局部辐射场,可以从一个自由移动的相机渲染。我们的模型可以用作生成新场景的先验知识,或者仅在稀疏的2D观察结果下完成场景。最近的工作表明,辐射场的生成模型可以捕获多视图一致性和视图相关照明等属性。但是,这些模型专用于单个对象(如汽车或人脸)的约束查看。由于现实室内环境的大小和复杂性,现有的模型缺乏充分捕捉它们的代表性能力。我们的分解方案可以扩展到更大,更复杂的场景,同时保留细节和多样性,并且学习的先验知识可以从与观察到的视点显著不同的视点进行高质量渲染。与现有的模型相比,GSN在几个不同的场景数据集上产生了定量的更高质量的场景渲染。

英文摘要:

We tackle the challenge of learning a distribution over complex, realistic, indoor scenes. In this paper, we introduce Generative Scene Networks (GSN), which learns to decompose scenes into a collection of many local radiance fields that can be rendered from a free moving camera. Our model can be used as a prior to generate new scenes, or to complete a scene given only sparse 2D observations. Recent work has shown that generative models of radiance fields can capture properties such as multi-view consistency and view-dependent lighting. However, these models are specialized for constrained viewing of single objects, such as cars or faces. Due to the size and complexity of realistic indoor environments, existing models lack the representational capacity to adequately capture them. Our decomposition scheme scales to larger and more complex scenes while preserving details and diversity, and the learned prior enables high-quality rendering from viewpoints that are significantly different from observed viewpoints. When compared to existing models, GSN produces quantitatively higher-quality scene renderings across several different scene datasets.

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。

↑