期刊
COMPUTER GRAPHICS FORUM
卷 40, 期 4, 页码 45-59出版社
WILEY
DOI: 10.1111/cgf.14340
关键词
Neural Rendering; Image-Based Rendering; Multi-View; Per-View Optimization
Recently, there has been a growing interest in neural rendering methods. This study introduces a general approach that utilizes MVS for initialization but allows further optimization of scene properties in the input view space, resulting in improved quality and speed in novel-view synthesis compared to previous methods.
There has recently been great interest in neural rendering methods. Some approaches use 3D geometry reconstructed with Multi-View Stereo (MVS) but cannot recover from the errors of this process, while others directly learn a volumetric neural representation, but suffer from expensive training and inference. We introduce a general approach that is initialized with MVS, but allows further optimization of scene properties in the space of input views, including depth and reprojected features, resulting in improved novel-view synthesis. A key element of our approach is our new differentiable point-based pipeline, based on bi-directional Elliptical Weighted Average splatting, a probabilistic depth test and effective camera selection. We use these elements together in our neural renderer, that outperforms all previous methods both in quality and speed in almost all scenes we tested. Our pipeline can be applied to multi-view harmonization and stylization in addition to novel-view synthesis.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据