47 citations · 78 across the 9 of their papers we have counts for
18 papers
Photo-realistic Neural Domain Randomization
Sergey Zakharov, Rares Ambrus, Vitor Guizilini +2
Synthetic data is a scalable alternative to manual supervision, but it requires overcoming the sim-to-real domain gap. This discrepancy between virtual and real worlds is addressed…
Warp-Refine Propagation: Semi-Supervised Auto-labeling via Cycle-consistency
Aditya Ganeshan, Alexis Vallet, Yasunori Kudo +5
Deep learning models for semantic segmentation rely on expensive, large-scale, manually annotated datasets. Labelling is a tedious process that can take hours per image. Automatica…
Is Pseudo-Lidar needed for Monocular 3D Object detection?
Dennis Park, Rares Ambrus, Vitor Guizilini +2
Recent progress in 3D object detection from single images leverages monocular depth estimation as a way to produce 3D pointclouds, turning cameras into pseudo-lidar sensors. These…
Full Surround Monodepth from Multiple Cameras
Vitor Guizilini, Igor Vasiljevic, Rares Ambrus +2
Self-supervised monocular depth and ego-motion estimation is a promising approach to replace or supplement expensive depth sensors such as LiDAR for robotics applications like auto…
Sparse Auxiliary Networks for Unified Monocular Depth Prediction and Completion
Vitor Guizilini, Rares Ambrus, Wolfram Burgard +1
Estimating scene geometry from data obtained with cost-effective sensors is key for robots and self-driving cars. In this paper, we study the problem of predicting dense depth from…
Geometric Unsupervised Domain Adaptation for Semantic Segmentation
Vitor Guizilini, Jie Li, Rares Ambrus +1
Simulators can efficiently generate large amounts of labeled synthetic data with perfect supervision for hard-to-label tasks like semantic segmentation. However, they introduce a d…