NeRF

🤖 Plain-English Summary

We present a method that achieves advanced results for synthesizing novel views of complex scenes by optimizing an underlying continuous volumetric scene function using a sparse set of input views. Because volume rendering is naturally differentiable, the only input required to optimize our representation is a set of images with known camera poses.

🔑 Key Findings

• 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.

🔗 Related Resources