Pretraining on large labeled datasets is a prerequisite to achieve good performance in many
computer vision tasks like image recognition, video understanding etc. However, pretraining …

We introduce HybridPose, a novel 6D object pose estimation approach. HybridPose utilizes
a hybrid intermediate representation to express different geometric information in the input …

Self-supervised representation learning solves auxiliary prediction tasks (known as pretext
tasks), that do not require labeled data, to learn semantic representations. These pretext …

We introduce H3DNet, which takes a colorless 3D point cloud as input and outputs a
collection of oriented object bounding boxes (or BB) and their semantic labels. The critical …

Visual perception entails solving a wide set of tasks (eg, object detection, depth estimation,
etc). The predictions made for different tasks out of one image are not independent, and …

This paper introduces HPNet, a novel deep-learning approach for segmenting a 3D shape
represented as a point cloud into primitive patches. The key to deep primitive segmentation …

We present QuantumSync, the first quantum algorithm for solving a synchronization problem
in the context of computer vision. In particular, we focus on permutation synchronization …

We propose a partial point cloud completion approach for scenes that are composed of
multiple objects. We focus on pairwise scenes where two objects are in close proximity and …

Developing deep neural networks to generate 3D scenes is a fundamental problem in
neural synthesis with immediate applications in architectural CAD, computer graphics, as …

A recent trend in optimizing maps such as dense correspondences between objects or
neural networks between pairs of domains is to optimize them jointly. In this context, there is …