Scribble-Supervised LiDAR Semantic Segmentation (Cattaneo)
FreeSOLO: Learning to Segment Objects without Annotations (Cattaneo)
TossingBot: Learning to Throw Arbitrary Objects with Residual Physics (Chisari)
Volumetric Grasping Network: Real-time 6 DOF Grasp Detection in Clutter (Chisari)
Video Autoencoder: Self-Supervised Disentanglement of Static 3D Structure and Motion (Gosala)
Audio-Visual Instance Discrimination with Cross-Modal Agreement (Gosala)
Do As I Can, Not As I Say: Grounding Language in Robotic Affordances (Honerkamp)
Adversarially Guided Actor Critic (Honerkamp)
How Far Can I Go ?: A Self-Supervised Approach for Deterministic Video Depth Forecasting (Hurtado)
Self-Supervised Multi-Object Tracking with Cross-Input Consistency (Hurtado)
Lifelong Graph Learning (Büchner)
3D Neural Scene Representations for Visuomotor Control (Büchner)