3 code implementations • 7 Jan 2021 • Austin Stone, Oscar Ramirez, Kurt Konolige, Rico Jonschkowski
Our experiments show that current RL methods for vision-based control perform poorly under distractions, and that their performance decreases with increasing distraction complexity, showing that new methods are needed to cope with the visual complexities of the real world.
5 code implementations • ECCV 2020 • Rico Jonschkowski, Austin Stone, Jonathan T. Barron, Ariel Gordon, Kurt Konolige, Anelia Angelova
We systematically compare and analyze a set of key components in unsupervised optical flow to identify which photometric loss, occlusion handling, and smoothness regularization is most effective.
Ranked #5 on Optical Flow Estimation on Sintel Clean unsupervised
1 code implementation • CVPR 2020 • Xingyu Liu, Rico Jonschkowski, Anelia Angelova, Kurt Konolige
We address two problems: first, we establish an easy method for capturing and labeling 3D keypoints on desktop objects with an RGB camera; and second, we develop a deep neural network, called $KeyPose$, that learns to accurately predict object poses using 3D keypoints, from stereo input, and works even for transparent objects.
no code implementations • 11 Nov 2017 • Stefan Hinterstoisser, Vincent Lepetit, Naresh Rajkumar, Kurt Konolige
Point Pair Features is a widely used method to detect 3D objects in point clouds, however they are prone to fail in presence of sensor noise and background clutter.
no code implementations • 29 Oct 2017 • Stefan Hinterstoisser, Vincent Lepetit, Paul Wohlhart, Kurt Konolige
Deep Learning methods usually require huge amounts of training data to perform at their full potential, and often require expensive manual labeling.
1 code implementation • 22 Sep 2017 • Konstantinos Bousmalis, Alex Irpan, Paul Wohlhart, Yunfei Bai, Matthew Kelcey, Mrinal Kalakrishnan, Laura Downs, Julian Ibarz, Peter Pastor, Kurt Konolige, Sergey Levine, Vincent Vanhoucke
We extensively evaluate our approaches with a total of more than 25, 000 physical test grasps, studying a range of simulation conditions and domain adaptation methods, including a novel extension of pixel-level domain adaptation that we term the GraspGAN.