Abstract & Method
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 (non-convolutional) 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.
Geometry Visualization
NeRFs are able to represent detailed scene geometry with complex occlusions. Here we visualize depth maps for rendered novel views computed as the expected termination of each camera ray in the encoded volume.
Your browser does not support the video tag.
Your browser does not support the video tag.
Our estimated scene geometry is detailed enough to support mixed-reality applications such as inserting virtual objects into real world scenes with compelling occlusion effects.
Your browser does not support the video tag.
GIPHY App Key not set. Please check settings