arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.04565cs.CV
收藏

MuRF:多基线辐射场

MuRF: Multi-Baseline Radiance Fields

ETH Zurich(苏黎世联邦理工学院);University of Tübingen(蒂宾根大学);Monash University(莫纳什大学);Shanghai Jiao Tong University(上海交通大学);Microsoft(微软公司)

Haofei Xu, Anpei Chen, Yuedong Chen, Christos Sakaridis, Yulun Zhang, Marc Pollefeys, Andreas Geiger, Fisher Yu

AI总结:

MuRF提出一种通用前馈稀疏视图合成方法,通过构建与目标视图对齐的视锥体体积并用卷积网络回归辐射场,在多种基线和多样化场景中取得最先进性能,并具备良好的零样本泛化能力。

摘要:

我们提出了多基线辐射场(MuRF),这是一种通用的前馈方法,用于在多种不同基线设置(小基线和大基线,以及不同数量的输入视图)下解决稀疏视图合成问题。为了渲染目标新视图,我们将三维空间离散化为与目标图像平面平行的平面,并相应地构建目标视锥体体积。这种目标体积表示与目标视图在空间上对齐,能够有效聚合来自输入视图的相关信息,从而实现高质量渲染。由于其轴对齐的特性,该表示还便于后续使用卷积网络进行辐射场回归。卷积网络建模的三维上下文使我们的方法能够合成比先前工作更清晰的场景结构。我们的MuRF在多种不同基线设置以及从简单物体(DTU)到复杂室内外场景(RealEstate10K和LLFF)的多样化场景中均取得了最先进的性能。我们还在Mip-NeRF 360数据集上展示了良好的零样本泛化能力,证明了MuRF的广泛适用性。

英文摘要:

We present Multi-Baseline Radiance Fields (MuRF), a general feed-forward approach to solving sparse view synthesis under multiple different baseline settings (small and large baselines, and different number of input views). To render a target novel view, we discretize the 3D space into planes parallel to the target image plane, and accordingly construct a target view frustum volume. Such a target volume representation is spatially aligned with the target view, which effectively aggregates relevant information from the input views for high-quality rendering. It also facilitates subsequent radiance field regression with a convolutional network thanks to its axis-aligned nature. The 3D context modeled by the convolutional network enables our method to synthesis sharper scene structures than prior works. Our MuRF achieves state-of-the-art performance across multiple different baseline settings and diverse scenarios ranging from simple objects (DTU) to complex indoor and outdoor scenes (RealEstate10K and LLFF). We also show promising zero-shot generalization abilities on the Mip-NeRF 360 dataset, demonstrating the general applicability of MuRF.

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。

↑