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.

我们提出了多基线辐射场（MuRF），这是一种解决在多个不同基线设置（小和大基线以及不同数量的输入视图）下的稀疏视图合成的通用前向方法。通过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图截锥体，以呈现目标新视图。这种目标体积表示与目标视图在空间上对齐，有效地聚合了输入视图的相关信息以实现高质量的渲染。由于其轴对齐的性质，它还便于用卷积网络进行后续的辐射场回归。通过卷积网络对建模的三维上下文，我们的方法能够合成比以往的工作更清晰的场景结构。我们的MuRF在多个不同的基线设置和从简单对象（DTU）到复杂的室内和室外场景（RealEstate10K和LLFF）的不同场景中实现了最先进的性能。我们还展示了在Mip-NeRF 360数据集上有良好的零样本泛化能力，证明了MuRF的广泛适用性。

MuRF：多基线辐射场