Point-Based Neural Rendering with Per-View Optimization

Simple item page
dc.contributor.authorKopanas, Georgiosen_US
dc.contributor.authorPhilip, Julienen_US
dc.contributor.authorLeimkühler, Thomasen_US
dc.contributor.authorDrettakis, Georgeen_US
dc.contributor.editorBousseau, Adrien and McGuire, Morganen_US
dc.date.accessioned2021-07-12T12:08:52Z
dc.date.available2021-07-12T12:08:52Z
dc.date.issued2021
dc.description.abstractThere 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.en_US
dc.description.number4
dc.description.sectionheadersNeural Rendering
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume40
dc.identifier.doi10.1111/cgf.14339
dc.identifier.issn1467-8659
dc.identifier.pages29-43
dc.identifier.urihttps://doi.org/10.1111/cgf.14339
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14339
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.titlePoint-Based Neural Rendering with Per-View Optimizationen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
v40i4pp029-043.pdf
Size:
11.03 MB
Format:
Adobe Portable Document Format
Download
Collections
40-Issue 4