78 datasets found

A 3D Gaussian Splatting (3DGS) scene reconstructed by the 3D Gaussian Splatting (3DGS).

A dataset for dynamic HDR scene representation, capturing images with varying exposures and nonuniform illumination.

A dataset for dynamic HDR scene representation, capturing images with varying exposures and nonuniform illumination.

A dataset for multiview segmentation and 3D inpainting with neural radiance fields.

The dataset used in the paper is a collection of images of objects in 3D space, with multiple views of each object.

The dataset used in the paper is a collection of images of objects in 3D space, with multiple views of each object.

The dataset used in the paper is a collection of images of objects in 3D space, with multiple views of each object.

The dataset used in this paper for testing the Spacecraft Pose Estimation network trained on the SPEED+ dataset.

The dataset used in this paper for training a Spacecraft Pose Estimation network from a sparse set of real images depicting an unknown target spacecraft.

The dataset used in the paper is a large-scale paired dataset for training a NeRF-agnostic restorer. It consists of 8 virtual scenes, each with 400 images.

The dataset used in the paper is a large-scale paired dataset for training a NeRF-agnostic restorer. It consists of 8 different forward-facing scenes with 20-62 high-quality...

Simulated multiview lidar dataset for transient neural radiance fields

The dataset used in the paper is a custom-built simulator dataset, which is used to train and test the neural radiance field (NeRF) model.

A novel end-to-end method that does not require prior camera parameters to deal with image sequences with complex trajectories.

PixelNeRF: Neural Radiance Fields from one or few images

The IBRNet dataset contains 10 scenes, each with 60 training views (with the object to be removed), 40 test views (without the object), and human-annotated object masks per view.

The SPIn-NeRF dataset contains 10 scenes, each with 60 training views (with the object to be removed), 40 test views (without the object), and human-annotated object masks per...

Neural Radiance Fields (NeRF) have shown remarkable suc-cess in representing 3D scenes and generating novel views. However, they often struggle with aliasing artifacts,...

The Kubric dataset offers training and validation data across various difficulty levels, featuring videos of objects interacting with each other.

A dataset of 3D shapes and textures for text-driven 3D manipulation.