68 datasets found

Real-time 3D scene reconstruction from monocular video

The dataset used for training the D2-Net model, consisting of 327,036 image pairs with at least 50% overlap in the sparse SfM point cloud.

The ETH3D Benchmark dataset contains a set of objects 3D coordinates, images in which these objects can be seen, the intrinsic parameters and the pose of each of the cameras...

Non-line-of-sight reconstruction using efficient transient rendering

3D-R2N2: A Unified Approach for Single and Multi-View 3D Object Reconstruction

Non-line-of-sight scene reconstruction using time-of-flight measurements

The dataset used in this paper for 3D mesh reconstruction from a single image.

Scannet: Richly-annotated 3D reconstructions of indoor scenes.

The dataset used in the paper is the DVGO dataset, which contains 3D scenes and is used for training and testing the proposed neural radiance field model.

The dataset used in the paper is the LF dataset, which contains real-world scenes and is used for training and testing the proposed neural radiance field model.

The dataset used in the paper is the LLFF dataset, which contains real-world scenes and is used for training and testing the proposed neural radiance field model.

A large-scale 3D model repository containing over 16,000 3D models.

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 InterHand2.6M dataset contains 366K training samples, 110K validation samples, and 261K test samples. It is the only interacting two-hand dataset with dense shape annotations.

Seeing 3D chairs: exemplar part-based 2D-3D alignment using a large dataset of CAD models

Deformable Neural Radiance Fields extend NeRF by modeling non-rigidly deforming scenes.

The DTU MVS dataset contains 49 images of physical objects in real environments.

The Tanks and Temples Advanced (T&T) dataset is a benchmark dataset for image-based 3D reconstruction. It contains 90% images for training and 10% images for evaluation.

NeRF LLFF dataset is a benchmark dataset for learning implicit 3D representations and addressing different tasks such as novel-view synthesis or depth-map estimation.

Simulated multiview lidar dataset for transient neural radiance fields