54 datasets found

The dataset used for 2D image fitting and NeRF training.

Reconstructing large-scale 3D scenes is essential for autonomous vehicles, especially when partial sensor data is lost.

Reconstructing large-scale 3D scenes is essential for autonomous vehicles, especially when partial sensor data is lost.

A dataset for generating controllable scenes using a composable NeRF representation.

A dataset of 121 video sequences of common household objects, captured by GoPro Hero9 action cameras at 30 FPS and 1920 × 1080 resolution.

The dataset used in the paper is not explicitly mentioned, but it is mentioned that the authors used real scenes and scenes from IN2N [9] and LLFF [29].

NeRF dataset for large-scale urban scene reconstruction

The dataset used in this study for hologram generation using NeRF technique.

NeRF-Synthetic benchmark dataset, containing 8 synthetic objects with images taken from different viewpoints uniformly distributed in the hemisphere.

CAwa-NeRF: Instant Learning of Compression-Aware NeRF Features

The dataset used in the paper is a collection of RGB images of a tabletop scene, along with their corresponding camera poses and 3D geometry.

Realistic real-time talking head synthesis with hash grid landmarks encoding and progressive multilayer conditioning

A digital replica of indoor spaces for training and testing NeRF-based models

Real-world camera motion blur and defocus blur datasets for training a sharp NeRF under blurry input.

Synthetic camera motion blur and defocus blur datasets for training a sharp NeRF under blurry input.

The LLFF-NeRF dataset consists of eight scenes captured with a handheld cellphone, with 20-62 images each. The resolution of each image in the dataset is 4032 × 3024.

The ShapeNeRF–Text dataset consists of 40K paired NeRFs and language annotations for ShapeNet objects.

A dataset of 3D human faces for training and testing the NeRFlame model.

The dataset used in the paper for cinematic motion transfer, consisting of NeRF representations of 3D scenes and reference video clips.

A dataset for dynamic scene reconstruction, including monocular multi-view images and camera poses.