1.5k citations
- Research!America (United States)US21 papers
- Samsung (South Korea)KR17 papers
- Korea Advanced Institute of Science and TechnologyKR9 papers
- Korea Institute of Science and TechnologyKR7 papers
- University of CambridgeGB5 papers
- University of Southern CaliforniaUS5 papers
- Imperial College LondonGB4 papers
- Purdue University West LafayetteUS4 papers
- Samsung Electronics (South Korea)KR4 papers
- Samsung (India)IN4 papers
- Stanford UniversityUS4 papers
- Texas A&M UniversityUS4 papers
14 papers · 2 filters
Surface HOF: Surface Reconstruction from a Single Image Using Higher Order Function Networks
Ziyun Wang, Volkan Isler, Daniel D. Lee
We address the problem of generating a high-resolution surface reconstruction from a single image. Our approach is to learn a Higher Order Function (HOF) which takes an image of an…
Training Deep SLAM on Single Frames
Igor Slinko, Anna Vorontsova, Dmitry Zhukov +2
Learning-based visual odometry and SLAM methods demonstrate a steady improvement over past years. However, collecting ground truth poses to train these methods is difficult and exp…
Measuring robustness of Visual SLAM
David Prokhorov, Dmitry Zhukov, Olga Barinova +2
Simultaneous localization and mapping (SLAM) is an essential component of robotic systems. In this work we perform a feasibility study of RGB-D SLAM for the task of indoor robot na…
MixMatch Domain Adaptaion: Prize-winning solution for both tracks of VisDA 2019 challenge
Danila Rukhovich, Danil Galeev
We present a domain adaptation (DA) system that can be used in multi-source and semi-supervised settings. Using the proposed method we achieved 2nd place on multi-source track and…
XNOR-Net++: Improved Binary Neural Networks
Adrian Bulat, Georgios Tzimiropoulos
This paper proposes an improved training algorithm for binary neural networks in which both weights and activations are binary numbers. A key but fairly overlooked feature of the c…
Scene Motion Decomposition for Learnable Visual Odometry
Igor Slinko, Anna Vorontsova, Filipp Konokhov +2
Optical Flow (OF) and depth are commonly used for visual odometry since they provide sufficient information about camera ego-motion in a rigid scene. We reformulate the problem of…