12 datasets found

Implicit neural 3D representation has achieved impressive results in surface or scene reconstruction and novel view synthesis, which typically uses the coordinate-based...

The dataset used in the paper for scene reconstruction.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors tested their model on various signal reconstruction tasks: 1D sinusoidal...

The Instant-NGP dataset is a dataset for instant neural graphics primitives, consisting of 8 scenes with varying complexity.

A large-scale dataset of multi-view images for 3D scene understanding.

A latent diffusion model that samples and reconstructs large real-world scenes represented as 3D Gaussians in as little as 0.2 seconds.

The Mutant and LEGO dataset is a dynamic scene dataset. It contains 90% images for training and 10% images for evaluation.

This dataset is used for novel view synthesis and scene reconstruction.

The dataset used in the paper for 3D scene generation from text descriptions.

Neural Radiance Fields (NeRFs) model a 3D scene as a volumetric function, which can be rendered from arbitrary viewpoints to generate highly-realistic images.

The DTU dataset is a large-scale dataset for multi-view stereo depth inference. It contains over 100 scans taken under 7 different lighting conditions and fixed camera...

The LLFF dataset contains 8 forward-facing scenes. Following [19, 26, 35, 42], we take every 8-th image as the novel views for testing. The input views are evenly sampled across...