35 citations · 140 across the 13 of their papers we have counts for
9 papers · 1 filter
Conditional Object-Centric Learning from Video
Thomas Kipf, Gamaleldin F. Elsayed, Aravindh Mahendran +6
Object-centric representations are a promising path toward more systematic generalization by providing flexible abstractions upon which compositional world models can be built. Rec…
SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping
Austin Stone, Daniel Maurer, Alper Ayvaci +2
We present SMURF, a method for unsupervised learning of optical flow that improves state of the art on all benchmarks by to (over the prior best method UFlow) and eve…
Adaptive Intermediate Representations for Video Understanding
Juhana Kangaspunta, AJ Piergiovanni, Rico Jonschkowski +2
A common strategy to video understanding is to incorporate spatial and motion information by fusing features derived from RGB frames and optical flow. In this work, we introduce a…
Learning Object-Centric Video Models by Contrasting Sets
Sindy Löwe, Klaus Greff, Rico Jonschkowski +2
Contrastive, self-supervised learning of object representations recently emerged as an attractive alternative to reconstruction-based training. Prior approaches focus on contrastin…
What Matters in Unsupervised Optical Flow
Rico Jonschkowski, Austin Stone, Jonathan T. Barron +3
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…
Differentiable Mapping Networks: Learning Structured Map Representations for Sparse Visual Localization
Peter Karkus, Anelia Angelova, Vincent Vanhoucke +1
Mapping and localization, preferably from a small number of observations, are fundamental tasks in robotics. We address these tasks by combining spatial structure (differentiable m…
KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent Objects
Xingyu Liu, Rico Jonschkowski, Anelia Angelova +1
Estimating the 3D pose of desktop objects is crucial for applications such as robotic manipulation. Many existing approaches to this problem require a depth map of the object for b…
Towards Object Detection from Motion
Rico Jonschkowski, Austin Stone
We present a novel approach to weakly supervised object detection. Instead of annotated images, our method only requires two short videos to learn to detect a new object: 1) a vide…
Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras
Ariel Gordon, Hanhan Li, Rico Jonschkowski +1
We present a novel method for simultaneous learning of depth, egomotion, object motion, and camera intrinsics from monocular videos, using only consistency across neighboring video…