17 datasets found

Tags: hand pose estimation

Filter Results

  • FPHA Dataset

    The FPHA dataset is a real-world dataset for studying hand-object interaction.

  • HO-3D and FPHA Datasets

    The HO-3D and FPHA datasets are real-world datasets for studying hand-object interaction.

  • REGION ENSEMBLE NETWORK: IMPROVING CONVOLUTIONAL NETWORK FOR HAND POSE ESTIMA...

    Hand pose estimation from monocular depth images is an important and challenging problem for human-computer interaction. Recently deep convolutional networks (ConvNet) with...

  • NYU

    The dataset used for testing the HandVoxNet approach for 3D hand shape and pose estimation from a single depth map.

  • ICVL

    A hand, which is an articulated object, is composed of six local parts: the palm and five independent fingers.

  • MuViHand

    The MuViHand dataset is a synthetic multi-view video-based hand pose dataset with 402,000 synthetic hand images available in 4,560 videos.

  • HaGRID

    A large-scale hand gesture dataset for hand gesture recognition, containing 554,800 images with bounding box and gesture annotations.

  • First-person hand benchmark (FHB)

    The FHB dataset contains egocentric RGB-D videos on a wide range of hand-object interactions.

  • NYU Hand Pose Dataset

    The NYU Hand Pose Dataset comprises 70,000 images captured with a depth sensor in VGA resolution accompanied by ground truth annotations of positions of hand joints.

  • Stereo-based Hand Tracking Benchmark

    A benchmark for evaluating hand pose tracking/estimation algorithms on passive stereo. Unlike existing benchmarks, it contains both stereo images from a binocular stereo camera...

  • DART

    DART is a larger open-domain dataset, where triples are composed of tree-structured ontology.

  • Re:InterHand

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

  • InterHand2.6M

    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

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

  • Honnotate

    The Honnotate dataset is a method for 3D annotation of hand and object poses.

  • Parallel mesh reconstruction streams for pose estimation of interacting hands

    A new multi-stream 3D mesh reconstruction network (MSMR-Net) for hand pose estimation from a single RGB image.

  • CORe50

    CORe50 is a video benchmark for continual learning, consisting of 164,866 128x128 images of 50 domestic objects belonging to 10 categories.
You can also access this registry using the API (see API Docs).