7 datasets found

A fast neural rendering framework for dynamic scenes, representing scenes with time-aware neural voxels to accelerate the training speed and maintain high rendering quality.

A new approach for creating an animatable and photo-realistic 3D head model from multi-view video footage of a real actor, together with a neural animation model based on...

A dataset of images captured with a cellphone camera and its built-in flash, used to train a neural reflectance field representation that models scene geometry and reflectance.

HumanNeRF: Efficiently Generated Human Radiance Field from Sparse Inputs

A novel framework for one- and few-shot neural rendering that predicts a neural representation of a 3D scene using Orthogonal Moments.

NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis

The Mip-NeRF360 dataset contains scenes taken from a 360 degree view, with emphasis on minimizing photometric variations.