Point-Based Neural Rendering with Per-View Optimization

Loading...
Thumbnail Image
Date
2021
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and John Wiley & Sons Ltd.
Abstract
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.
Description

        
@article{
10.1111:cgf.14339
, journal = {Computer Graphics Forum}, title = {{
Point-Based Neural Rendering with Per-View Optimization
}}, author = {
Kopanas, Georgios
and
Philip, Julien
and
Leimkühler, Thomas
and
Drettakis, George
}, year = {
2021
}, publisher = {
The Eurographics Association and John Wiley & Sons Ltd.
}, ISSN = {
1467-8659
}, DOI = {
10.1111/cgf.14339
} }
Citation
Collections