MINE：面向连续深度的MPI与NeRF用于新视图合成
MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis
摘要：
在本文中，我们提出了MINE执行新的视图合成和深度估计通过密集的三维重建从一个单一的图像。我们的方法是通过引入神经辐射场（NeRF）的多平面图像（MPI）的连续深度推广。给定单个图像作为输入，MINE预测任意深度值的4通道图像（RGB和体积密度），以联合重建相机截头体并填充遮挡内容。然后，可以使用可微分渲染将重建和修复的平截头体容易地渲染成新颖的RGB或深度视图。在RealEstate 10 K，KITTI和Flowers光场上的大量实验表明，我们的MINE在新颖的视图合成方面远远优于最先进的技术。在没有注释深度监督的情况下，我们还在iBims-1和NYU-v2上的深度估计中取得了有竞争力的结果。我们的源代码可以在https://github.com/vincentfung13/MINE上找到
英文摘要：
In this paper, we propose MINE to perform novel view synthesis and depth estimation via dense 3D reconstruction from a single image. Our approach is a continuous depth generalization of the Multiplane Images (MPI) by introducing the NEural radiance fields (NeRF). Given a single image as input, MINE predicts a 4-channel image (RGB and volume density) at arbitrary depth values to jointly reconstruct the camera frustum and fill in occluded contents. The reconstructed and inpainted frustum can then be easily rendered into novel RGB or depth views using differentiable rendering. Extensive experiments on RealEstate10K, KITTI and Flowers Light Fields show that our MINE outperforms state-of-the-art by a large margin in novel view synthesis. We also achieve competitive results in depth estimation on iBims-1 and NYU-v2 without annotated depth supervision. Our source code is available at https://github.com/vincentfung13/MINE
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。
