85 datasets found

The DTU dataset is a large-scale multi-view stereopsis evaluation dataset.

A dataset for training a visual transformer to predict a scene descriptor from a single wire-frame image.

The dataset contains data collected in various behavioral and social scenarios, including polls of public opinion, visual illusions, conjoint choices, and psychophysical matching.

The MonoCap Dataset includes four multi-view videos from DeepCap and DynaCap datasets, collected by Peng et al. This dataset provides essential details like camera parameters,...

The ZJU-MoCap dataset is a prominent benchmark in human modeling from videos. The dataset includes 6 human subjects, each with 100 frames collected from one camera for training...

Re:InterHand dataset is a large-scale dataset for 3D interacting hand pose estimation from a single RGB image.

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.

RenderIH dataset is a large-scale synthetic dataset for 3D interacting hand pose estimation from a single RGB image.

UP-3D: A Large-Scale 3D Human Body Dataset for Pose Estimation. UP-3D: A Large-Scale 3D Human Body Dataset for Pose Estimation. UP-3D: A Large-Scale 3D Human Body Dataset for...

The SLAM dataset is a collection of images and their corresponding 3D point clouds, used for training and testing SLAM algorithms.

The dataset used in this paper is an ICL-NUIM dataset, which contains images and depth maps.

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

The dataset used in this paper is the spacenet multi-view dataset, which includes both multi-date and single-date multi-view RGB images.

3D human pose and mesh estimation, the task of recon-structing human pose in 3D space given a 2D image of the person, is an ill-posed problem, and many data-driven ap-proaches...

The dataset used in this paper for multi-sensor next-best-view planning as matroid-constrained submodular maximization.

The DexYCB dataset is a large-scale dataset of hand-grasping postures captured using a synchronized setup of 8 cameras.

The dataset used in the paper is the EDS dataset, which contains aligned frames and events from the same viewpoint.

The dataset used in the paper is a simulation of five sequences with different motion trajectories and background textures using the event camera simulator ESIM.

The Dynamic FAUST dataset contains raw-scanned and registered meshes for 129 sequences of 10 humans with various motions.

Two publicly available datasets with histological sections and an ex vivo 3D MRI of the same subject. A 3D similarity transform between the stack of histological sections and...