HOnnotate: A method for 3D Annotation of Hand and Object Poses
This addresses the lack of annotated real images for 3D hand-object pose estimation, which is crucial for robotics and human-computer interaction, but it is incremental as it builds on existing annotation techniques.
The authors tackled the problem of annotating images with 3D hand and object poses by proposing a method that uses RGB-D cameras and joint optimization to create the HO-3D dataset, which includes 77,558 frames and 10 objects, and they developed an RGB-based method that generalizes to unseen objects.
We propose a method for annotating images of a hand manipulating an object with the 3D poses of both the hand and the object, together with a dataset created using this method. Our motivation is the current lack of annotated real images for this problem, as estimating the 3D poses is challenging, mostly because of the mutual occlusions between the hand and the object. To tackle this challenge, we capture sequences with one or several RGB-D cameras and jointly optimize the 3D hand and object poses over all the frames simultaneously. This method allows us to automatically annotate each frame with accurate estimates of the poses, despite large mutual occlusions. With this method, we created HO-3D, the first markerless dataset of color images with 3D annotations for both the hand and object. This dataset is currently made of 77,558 frames, 68 sequences, 10 persons, and 10 objects. Using our dataset, we develop a single RGB image-based method to predict the hand pose when interacting with objects under severe occlusions and show it generalizes to objects not seen in the dataset.