research
∙
05/14/2021
SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping
We present SMURF, a method for unsupervised learning of optical flow tha...
share
research
∙
04/16/2021
MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale
General-purpose robotic systems must master a large repertoire of divers...
research
∙
04/14/2021
Adaptive Intermediate Representations for Video Understanding
A common strategy to video understanding is to incorporate spatial and m...
research
∙
01/07/2021
The Distracting Control Suite – A Challenging Benchmark for Reinforcement Learning from Pixels
Robots have to face challenging perceptual settings, including changes i...
research
∙
11/14/2020
A Geometric Perspective on Self-Supervised Policy Adaptation
One of the most challenging aspects of real-world reinforcement learning...
research
∙
06/08/2020
What Matters in Unsupervised Optical Flow
We systematically compare and analyze a set of key components in unsuper...
research
∙
05/19/2020
Differentiable Mapping Networks: Learning Structured Map Representations for Sparse Visual Localization
Mapping and localization, preferably from a small number of observations...
research
∙
04/24/2020
Towards Differentiable Resampling
Resampling is a key component of sample-based recursive state estimation...
research
∙
12/05/2019
KeyPose: Multi-view 3D Labeling and Keypoint Estimation for Transparent Objects
Estimating the 3D pose of desktop objects is crucial for applications su...
research
∙
09/17/2019
Towards Object Detection from Motion
We present a novel approach to weakly supervised object detection. Inste...
research
∙
04/10/2019
Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras
We present a novel method for simultaneous learning of depth, egomotion,...
research
∙
05/28/2018
Differentiable Particle Filters: End-to-End Learning with Algorithmic Priors
We present differentiable particle filters (DPFs): a differentiable impl...
research
∙
05/27/2017
PVEs: Position-Velocity Encoders for Unsupervised Learning of Structured State Representations
We propose position-velocity encoders (PVEs) which learn---without super...
research
∙
11/19/2015