
-
3D-OES: Viewpoint-Invariant Object-Factorized Environment Simulators
We propose an action-conditioned dynamics model that predicts scene chan...
read it
-
3D Object Recognition By Corresponding and Quantizing Neural 3D Scene Representations
We propose a system that learns to detect objects and infer their 3D pos...
read it
-
Embodied Language Grounding with Implicit 3D Visual Feature Representations
Consider the utterance "the tomato is to the left of the pot." Humans ca...
read it
-
Embodied View-Contrastive 3D Feature Learning
Humans can effortlessly imagine the occluded side of objects in a photog...
read it
-
Learning Spatial Common Sense with Geometry-Aware Recurrent Networks
We integrate two powerful ideas, geometry and deep visual representation...
read it
-
Reward Learning from Narrated Demonstrations
Humans effortlessly "program" one another by communicating goals and des...
read it
-
Self-supervised Learning of Motion Capture
Current state-of-the-art solutions for motion capture from a single came...
read it
-
Adversarial Inverse Graphics Networks: Learning 2D-to-3D Lifting and Image-to-Image Translation from Unpaired Supervision
Researchers have developed excellent feed-forward models that learn to m...
read it
-
Spectral Methods for Nonparametric Models
Nonparametric models are versatile, albeit computationally expensive, to...
read it