Scientific discovery and engineering design are currently limited by the time and cost of
physical experiments. Numerical simulations are an alternative approach but are usually …

Unsupervised generation of high-quality multi-view-consistent images and 3D shapes using
only collections of single-view 2D photographs has been a long-standing challenge …

Though neural radiance fields (" NeRF") have demonstrated impressive view synthesis
results on objects and small bounded regions of space, they struggle on" unbounded" …

We present a super-fast convergence approach to reconstructing the per-scene radiance
field from a set of images that capture the scene with known poses. This task, which is often …

Abstract We present Block-NeRF, a variant of Neural Radiance Fields that can represent
large-scale environments. Specifically, we demonstrate that when scaling NeRF to render …

We propose a method for editing NeRF scenes with text-instructions. Given a NeRF of a
scene and the collection of images used to reconstruct it, our method uses an image …

The rendering procedure used by neural radiance fields (NeRF) samples a scene with a
single ray per pixel and may therefore produce renderings that are excessively blurred or …

Neural volume rendering became increasingly popular recently due to its success in
synthesizing novel views of a scene from a sparse set of input images. So far, the geometry …

We introduce a method to render Neural Radiance Fields (NeRFs) in real time using
PlenOctrees, an octree-based 3D representation which supports view-dependent effects …

We introduce a free-viewpoint rendering method--HumanNeRF--that works on a given
monocular video of a human performing complex body motions, eg a video from YouTube …