activity
20172026
most citedCNN-SLAM: Real-time dense monocular SLAM with learned depth prediction

69 citations · 186 across the 18 of their papers we have counts for

collaborators
Showing 2018Show all

2 papers · 1 filter

cs.CV2018★ 63 cited

Peeking Behind Objects: Layered Depth Prediction from a Single Image

Helisa Dhamo, Keisuke Tateno, Iro Laina +2

While conventional depth estimation can infer the geometry of a scene from a single RGB image, it fails to estimate scene regions that are occluded by foreground objects. This limi…

cs.CV2018★ 5 cited

Fast and Accurate Semantic Mapping through Geometric-based Incremental Segmentation

Yoshikatsu Nakajima, Keisuke Tateno, Federico Tombari +1

We propose an efficient and scalable method for incrementally building a dense, semantically annotated 3D map in real-time. The proposed method assigns class probabilities to each…