Related papers: Hypernom: Mapping VR Headset Orientation to S^3

High annotation costs and limited labels for dense 3D medical imaging tasks have recently motivated an assortment of 3D self-supervised pretraining methods that improve transfer learning performance. However, these methods commonly lack…

Understanding the intricate mappings between visual stimuli and neural responses is a fundamental challenge in cognitive neuroscience. While current approaches predominantly align images and functional magnetic resonance imaging (fMRI)…

Humans learn to recognize and manipulate new objects in lifelong settings without forgetting the previously gained knowledge under non-stationary and sequential conditions. In autonomous systems, the agents also need to mitigate similar…

Reconstructing 3D objects is an important computer vision task that has wide application in AR/VR. Deep learning algorithm developed for this task usually relies on an unrealistic synthetic dataset, such as ShapeNet and Things3D. On the…

Manipulation planning is the task of computing robot trajectories that move a set of objects to their target configuration while satisfying physically feasibility. In contrast to existing works that assume known object templates, we are…

Augmented reality (AR) games, particularly those designed for head-mounted displays, have grown increasingly prevalent. However, most existing systems depend on pre-scanned, static environments and rely heavily on continuous tracking or…

In this paper, we investigate the utility of head-mounted display (HMD) interfaces for navigation of mobile robots. We focus on the selection of waypoint positions for the robot, whilst maintaining an egocentric view of the robot's…

Localizing objects and estimating their extent in 3D is an important step towards high-level 3D scene understanding, which has many applications in Augmented Reality and Robotics. We present ODAM, a system for 3D Object Detection,…

Sophisticated 3D visualization applications usually provide coordinated 2D and 3D views. Normally 3D input device is used for 3D tasks since they perform better than traditional 2D input devices. However, they do not perform better for 2D…

As part of human core knowledge, the representation of objects is the building block of mental representation that supports high-level concepts and symbolic reasoning. While humans develop the ability of perceiving objects situated in 3D…

Human pose estimation using deep neural networks aims to map input images with large variations into multiple body keypoints which must satisfy a set of geometric constraints and inter-dependency imposed by the human body model. This is a…

Backpropagation-based supervised learning has achieved great success in computer vision tasks. However, its biological plausibility is always controversial. Recently, the bio-inspired Hebbian learning rule (HLR) has received extensive…

This paper studies the problem for an affine hypersurface system to reach a polytopic target set starting from inside a polytope in the state space. We present an exhaustive solution which begins with a characterization of states which can…

Autonomous robots that interact with their environment require a detailed semantic scene model. For this, volumetric semantic maps are frequently used. The scene understanding can further be improved by including object-level information in…

Oculus rift: Virtual reality (VR) is a burgeoning field that has the inherent potential of manipulating peoples mind with a superlative 3D experience. Oculus rift is one such application that assists in achieving the same. With the fleeting…

Object Goal Navigation (ObjectNav) task is to navigate an agent to an object category in unseen environments without a pre-built map. In this paper, we solve this task by predicting the distance to the target using semantically-related…

To render a spherical (360 degree or omnidirectional) image on planar displays, a 2D image -- called as viewport -- must be obtained by projecting a sphere region on a plane, according to the users viewing direction and a predefined field…

4D modeling of human-object interactions is critical for numerous applications. However, efficient volumetric capture and rendering of complex interaction scenarios, especially from sparse inputs, remain challenging. In this paper, we…

Visual navigation has received significant attention recently. Most of the prior works focus on predicting navigation actions based on semantic features extracted from visual encoders. However, these approaches often rely on large datasets…

Hand-object pose estimation (HOPE) aims to jointly detect the poses of both a hand and of a held object. In this paper, we propose a lightweight model called HOPE-Net which jointly estimates hand and object pose in 2D and 3D in real-time.…