13 citations · 19 across the 5 of their papers we have counts for
6 papers · 1 filter
GEARS: Local Geometry-aware Hand-object Interaction Synthesis
Keyang Zhou, Bharat Lal Bhatnagar, Jan Eric Lenssen +1
Generating realistic hand motion sequences in interaction with objects has gained increasing attention with the growing interest in digital humans. Prior work has illustrated the e…
TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement
Keyang Zhou, Bharat Lal Bhatnagar, Jan Eric Lenssen +1
We present TOCH, a method for refining incorrect 3D hand-object interaction sequences using a data prior. Existing hand trackers, especially those that rely on very few cameras, of…
Panoramic Depth Estimation via Supervised and Unsupervised Learning in Indoor Scenes
Keyang Zhou, Kailun Yang, Kaiwei Wang
Depth estimation, as a necessary clue to convert 2D images into the 3D space, has been applied in many machine vision areas. However, to achieve an entire surrounding 360-degree ge…
Adjoint Rigid Transform Network: Task-conditioned Alignment of 3D Shapes
Keyang Zhou, Bharat Lal Bhatnagar, Bernt Schiele +1
Most learning methods for 3D data (point clouds, meshes) suffer significant performance drops when the data is not carefully aligned to a canonical orientation. Aligning real world…
Unsupervised Shape and Pose Disentanglement for 3D Meshes
Keyang Zhou, Bharat Lal Bhatnagar, Gerard Pons-Moll
Parametric models of humans, faces, hands and animals have been widely used for a range of tasks such as image-based reconstruction, shape correspondence estimation, and animation.…
Efficient Image Evidence Analysis of CNN Classification Results
Keyang Zhou, Bernhard Kainz
Convolutional neural networks (CNNs) define the current state-of-the-art for image recognition. With their emerging popularity, especially for critical applications like medical im…