23.6k citations
- Google (United States)US44 papers
- ETH ZurichCH19 papers
- École Polytechnique Fédérale de LausanneCH11 papers
- Technical University of MunichDE11 papers
- Ames Research CenterUS8 papers
- BMW Group (Germany)DE5 papers
- Centre National de la Recherche ScientifiqueFR5 papers
- Durham UniversityGB5 papers
- Google (United Kingdom)GB5 papers
- Johns Hopkins UniversityUS5 papers
- Sapienza University of RomeIT4 papers
- University College LondonGB4 papers
5 papers · 2 filters
Panoster: End-to-end Panoptic Segmentation of LiDAR Point Clouds
Stefano Gasperini, Mohammad-Ali Nikouei Mahani, Alvaro Marcos-Ramiro +2
Panoptic segmentation has recently unified semantic and instance segmentation, previously addressed separately, thus taking a step further towards creating more comprehensive and e…
SCFusion: Real-time Incremental Scene Reconstruction with Semantic Completion
Shun-Cheng Wu, Keisuke Tateno, Nassir Navab +1
Real-time scene reconstruction from depth data inevitably suffers from occlusion, thus leading to incomplete 3D models. Partial reconstructions, in turn, limit the performance of a…
Training general representations for remote sensing using in-domain knowledge
Maxim Neumann, André Susano Pinto, Xiaohua Zhai +1
Automatically finding good and general remote sensing representations allows to perform transfer learning on a wide range of applications - improving the accuracy and reducing the…
ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variation
Xucong Zhang, Seonwook Park, Thabo Beeler +3
Gaze estimation is a fundamental task in many applications of computer vision, human computer interaction and robotics. Many state-of-the-art methods are trained and tested on cust…
Image Matching across Wide Baselines: From Paper to Practice
Yuhe Jin, Dmytro Mishkin, Anastasiia Mishchuk +4
We introduce a comprehensive benchmark for local features and robust estimation algorithms, focusing on the downstream task -- the accuracy of the reconstructed camera pose -- as o…