Radiance Fields (Gaussian Splatting and NeRFs)

How Do Radiance Fields Work?

Radiance Fields create a volumetric representation of a scene using a deep neural network. This network takes as input a 5D coordinate—comprised of the spatial location and the viewing direction—and outputs the scene's volume density and emitted radiance at that point.

What's Next for Radiance Fields?

The potential ceiling for Radiance Fields remains unknown. It is likely that new forms of radiance fields will continue to emerge.

What's Next for Gaussian Splatting?

On July 10th, 2024, NVIDIA Research unveiled 3D Gaussian Ray Tracing, as a departure from Splatting. As the name implies, it utilizes ray tracing rather than the rasterization that has traditionally been used with Gaussian Splatting. There are several exciting advancements and functionalities that become readily available.

What's Next for NeRFs?

While NeRFs offer amazing performance in rendering static scenes, their ability to handle dynamic or moving objects in real-world scenarios is still an area for future exploration. The concept of viewing direction is paramount in NeRFs, as the representation needs to accurately capture how light, from different directions, interacts with the scene geometry, be it buildings, a person, or even a simple table.