Wesley Khademi
Jonathan Ventura
ABSTRACT
We extend Neural Radiance Fields (NeRF) with a cylindrical parameterization that enables rendering photorealistic novel views of 360° outward facing scenes. We further introduce a learned exposure compensation parameter to account for the varying exposure in training images that may occur from casually capturing a scene. We evaluate our method on a variety of 360° casually captured scenes.
Supplemental Material
Available for Download
- N. Max. 1995. Optical models for direct volume rendering. IEEE Transactions on Visualization and Computer Graphics 1, 2(1995), 99–108. https://doi.org/10.1109/2945.468400Google Scholar
Digital Library
- Ben Mildenhall, Pratul P Srinivasan, Matthew Tancik, Jonathan T Barron, Ravi Ramamoorthi, and Ren Ng. 2020. Nerf: Representing scenes as neural radiance fields for view synthesis. In European Conference on Computer Vision. Springer, 405–421.Google ScholarDigital Library
- Kai Zhang, Gernot Riegler, Noah Snavely, and Vladlen Koltun. 2020. NeRF++: Analyzing and Improving Neural Radiance Fields. arxiv:2010.07492 [cs.CV]Google Scholar
Index Terms
View Synthesis In Casually Captured Scenes Using a Cylindrical Neural Radiance Field With Exposure Compensation
Recommendations
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
Computer Vision – ECCV 2020AbstractWe present a method that achieves state-of-the-art results for synthesizing novel views of complex scenes by optimizing an underlying continuous volumetric scene function using a sparse set of input views. Our algorithm represents a scene using a ...
Precomputed radiance transfer for dynamic scenes taking into account light interreflection
EGSR'07: Proceedings of the 18th Eurographics conference on Rendering TechniquesFast rendering of dynamic scenes taking into account global illumination is one of the most challenging tasks in computer graphics. This paper proposes a new precomputed radiance transfer (PRT) method for rendering dynamic scenes of rigid objects taking ...
Coherent radiance capture of scenes under changing illumination conditions for relighting applications
Relighting algorithms make it possible to take a model of a real-world scene and virtually modify its lighting. Unlike other methods that require controlled conditions, we introduce a new radiance capture method that allows the user to capture parts of ...
Comments