Richard Szeliski
Richard Szeliski
joined Google Research as a Distinguished Scientist in June 2022.
He is also an Affiliate Professor at the University of Washington.
Prior to Google, he worked for over 30 years in research at Facebook, Microsoft Research, and Digital Equipment.
His main research interests
include computational photography, image-based modeling, and neural rendering. He is also the author of
Computer Vision: Algorithms and Applications.
Research Areas
Authored Publications
Sort By
Binary Opacity Grids: Capturing Fine Geometric Detail for Mesh-Based View Synthesis
Christian Reiser
Stephan Garbin
Pratul Srinivasan
Dor Verbin
Ben Mildenhall
Peter Hedman
Andreas Geiger
2024
Preview abstract
While surface-based view synthesis algorithms are appealing due to their low computational requirements, they often struggle to reproduce thin structures. In contrast, more expensive methods that model the scene’s geometry as a volumetric density field (e.g. NeRF) excel at reconstructing fine geometric detail. However, density fields often represent geometry in a "fuzzy" manner, which hinders exact localization of the surface. In this work, we modify density fields to encourage them to converge towards surfaces, without compromising their ability to reconstruct thin structures. First, we employ a discrete opacity grid representation instead of a continuous density field, which allows opacity values to discontinuously transition from zero to one at the surface. Second, we anti-alias by casting multiple rays per pixel, which allows occlusion boundaries and subpixel structures to be modelled without using semi-transparent voxels. Third, we minimize the binary entropy of the opacity values, which facilitates the extraction of surface geometry by encouraging opacity values to binarize towards the end of training. Lastly, we develop a fusion-based meshing strategy followed by mesh simplification and appearance model fitting. The compact meshes produced by our model can be rendered in real-time on mobile devices and achieve significantly higher view synthesis quality compared to existing mesh-based approaches. Our interactive webdemo is available at https://binary-opacity-grid.github.io.
View details
