Project Aria pushes the frontiers of Egocentric AI with large-scale
real...
Egocentric, multi-modal data as available on future augmented reality (A...
We introduce the Aria Digital Twin (ADT) - an egocentric dataset capture...
We present EgoHumans, a new multi-view multi-human video benchmark to ad...
Humans can orient themselves in their 3D environments using simple 2D ma...
This paper presents a framework that combines traditional keypoint-based...
Learning geometry, motion, and appearance priors of object classes is
im...
This paper proposes a do-it-all neural model of human hands, named LISA....
We propose a novel explicit dense 3D reconstruction approach that proces...
Localizing objects and estimating their extent in 3D is an important ste...
Object-oriented maps are important for scene understanding since they jo...
Efficiently reconstructing complex and intricate surfaces at scale is a
...
We introduce Replica, a dataset of 18 highly photo-realistic 3D indoor s...
We propose a system that uses a convolution neural network (CNN) to esti...
Computer graphics, 3D computer vision and robotics communities have prod...
We present an approach for interactively scanning highly reflective obje...