153 datasets found

The dataset is used to test the performance of the machine learning model for strain estimation and frame selection in ultrasound elastography.

The dataset used in the paper is ScanNetV2, a real-world dataset for indoor scenes. It contains 1205 training scenes and 312 testing scenes, with instance-level object bounding...

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.

Generating consistent multiple views for 3D reconstruction tasks is still a challenge to existing image-to-3D diffusion models.

The dataset used in the paper for interactive gibson benchmark.

The dataset used in the paper for detailed spatio-temporal reconstruction of eyelids.

A dataset of synthetic photorealistic images for training and testing material-aware diffusion models

The dataset used in the paper for training and testing the NeRF model.

The 3D-EPN dataset is a point cloud completion benchmark derived from the ShapeNet dataset.

The dataset used for head pose estimation and 3D neural surface reconstruction via monocular camera in situ for navigation and safe insertion into natural openings.

Simulated multiview lidar dataset for transient neural radiance fields

ARKITScenes: A diverse real-world dataset for 3D indoor scene understanding using mobile RGB-D data

PixelNeRF: Neural Radiance Fields from one or few images

SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction

fMRI-Shape dataset, a pioneering dataset specifically designed for Recon3DMind, which pairs fMRI data with 3D visuals.

3D-FRONT is a synthetic dataset composed of 6,813 houses with 14,629 rooms, where each room is arranged by a collection of high-quality 3D furniture objects from the 3D-FUTURE...

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

The RenderDiffusion dataset is a dataset used in the paper LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation

The dataset contains five tabletop real scenes imaged by 352 cameras in a dome.

The dataset contains 80 real-world scenes with image sequences and structured light 3D scans as reference data.