97 citations
- Denso (Germany)DE3 papers
- Tokyo Institute of TechnologyJP3 papers
- Nitto (Japan)JP2 papers
- Tohoku UniversityJP2 papers
- Denso (Japan)JP1 paper
- Harvard University PressUS1 paper
- Institute of Space and Astronautical ScienceJP1 paper
- Japan Advanced Institute of Science and TechnologyJP1 paper
- Nagoya City UniversityJP1 paper
- National Astronomical Observatory of JapanJP1 paper
- Sasol (Germany)DE1 paper
- The Graduate University for Advanced Studies, SOKENDAIJP1 paper
Showing cs.CVShow all
3 papers · 1 filter
cs.CV2023
Pose Constraints for Consistent Self-supervised Monocular Depth and Ego-motion
Zeeshan Khan Suri
Self-supervised monocular depth estimation approaches suffer not only from scale ambiguity but also infer temporally inconsistent depth maps w.r.t. scale. While disambiguating scal…
cs.CV2019★ 4 cited
Tabulated MLP for Fast Point Feature Embedding
Yusuke Sekikawa, Teppei Suzuki
Aiming at a drastic speedup for point-data embeddings at test time, we propose a new framework that uses a pair of multi-layer perceptron (MLP) and look-up table (LUT) to transform…
cs.CV2019★ 3 cited
Adversarial Transformations for Semi-Supervised Learning
Teppei Suzuki, Ikuro Sato
We propose a Regularization framework based on Adversarial Transformations (RAT) for semi-supervised learning. RAT is designed to enhance robustness of the output distribution of c…