Description: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction
dataset (50) hand-object interaction (2)
To ensure latest version, please use sha256sum to calculate the checksum of the anno_v2.1.zip . You will get:
$ sha256sum anno_v2.1.zip --tag SHA256 (anno_v2.1.zip) = dc64402d65cff3c1e2dd40fb560fcc81e3757e1936f44d353c381874489d71ea. OakInk-Shape -- Geometry-based dataset Meta files for organizing and indexing the objects: metaV2.zip (15K) All hand parameters (pose, shape, root transf): oakink_shape_v2.zip (46M) All the real object models: OakInkObjectsV2.zip (1G) All the virtual object models: OakInkVirtualObjectsV2.zip (1G) After downloading all the above .zip files, you need to arrange them in the following struc
OakInk-Image provides data splits for two categories of tasks: Hand Mesh Recovery and Hand-Object Pose Estimation . The dataset contains in total 314,404 frames if no filtering is applied, in which 157,600 frames are from two-hand sequences. For single view tasks, we filter out frames that have less than 50% of joints falling in the bounds of the images. Note these frames might still be useful in multiview tasks. Refer to oikit repo for the usage of these split files.