activity
20182021
most citedDETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries

74 citations · 147 across the 8 of their papers we have counts for

collaborators

16 papers

cs.CV202174 cited

DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries

Yue Wang, Vitor Guizilini, Tianyuan Zhang +3

We introduce a framework for multi-camera 3D object detection. In contrast to existing works, which estimate 3D bounding boxes directly from monocular images or use depth predictio…

cs.CV2021

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…

cs.CV20211 cited

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…

cs.CV2021

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…

cs.CV2021

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…

cs.RO2021

Monocular Depth Estimation for Soft Visuotactile Sensors

Rares Ambrus, Vitor Guizilini, Naveen Kuppuswamy +3

Fluid-filled soft visuotactile sensors such as the Soft-bubbles alleviate key challenges for robust manipulation, as they enable reliable grasps along with the ability to obtain hi…