Haibin Huang

TL;DR: PVN3D as mentioned in this paper proposes a deep Hough voting network to detect 3D keypoints of objects and then estimate the 6D pose parameters within a least-squares fitting manner.

TL;DR: This work proposes a data-driven method for recovering missing parts of 3D shapes based on a new deep learning architecture consisting of a global structure inference network and a local geometry refinement network that outperforms existing state-of-the-art work on shape completion.

TL;DR: This work takes an alternative approach to the problem of learning generative models of 3D shapes: learning a generative model over multi-view depth maps or their corresponding silhouettes, and using a deterministic rendering function to produce3D shapes from these images.

TL;DR: A new local descriptor for 3D shapes is presented, directly applicable to a wide range of shape analysis problems such as point correspondences, semantic segmentation, affordance prediction, and shape-to-scan matching by a convolutional network trained to embed geometrically and semantically similar points close to one another in descriptor space.

TL;DR: FFB6D as discussed by the authors proposes a bidirectional fusion network to combine appearance and geometry information for representation learning as well as output representation selection, which can leverage local and global complementary in-formation from the other one to obtain better representations.