Communications of the ACM· 2021Q1
NeRF
- 5,949citations
- Q1SCImago
- 2021year
Short summary
A new method uses a deep neural network to represent complex 3D scenes as a continuous volumetric function, enabling photorealistic novel view synthesis from sparse input images.
AI-generated from the title and abstract; the full text is not read.
Key points
- Represents scenes as continuous 5D volumetric functions learned by deep networks.
- Synthesizes novel views by querying the network along camera rays and using volume rendering.
- Requires only images with known camera poses for optimization.
- Achieves state-of-the-art results in photorealistic novel view synthesis.
AI-generated from the title and abstract; the full text is not read.
Abstract
We 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 fully connected (nonconvolutional) deep network, whose input is a single continuous 5D coordinate (spatial location ( x , y , z ) and viewing direction ( θ, ϕ )) and whose output is the volume density and view-dependent emitted radiance at that spatial location. We synthesize views by querying 5D coordinates along camera rays and use classic volume rendering techniques to project the output colors and densities into an image. Because volume rendering is naturally differentiable, the only input required to optimize our representation is a set of images with known camera poses. We describe how to effectively optimize neural radiance fields to render photorealistic novel views of scenes with complicated geometry and appearance, and demonstrate results that outperform prior work on neural rendering and view synthesis.
The authors' abstract, as published at the source. Communications of the ACM, 2021 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computer Graphics and Computer-Aided Design
Computer Graphics and Computer-Aided DesignComputer Science