Search Results for author: Keisuke Tateno

Found 7 papers, 2 papers with code

A Divide et Impera Approach for 3D Shape Reconstruction from Multiple Views

no code implementations17 Nov 2020 Riccardo Spezialetti, David Joseph Tan, Alessio Tonioni, Keisuke Tateno, Federico Tombari

Estimating the 3D shape of an object from a single or multiple images has gained popularity thanks to the recent breakthroughs powered by deep learning.

3D Shape Reconstruction Pose Estimation

SCFusion: Real-time Incremental Scene Reconstruction with Semantic Completion

2 code implementations26 Oct 2020 Shun-Cheng Wu, Keisuke Tateno, Nassir Navab, Federico Tombari

We propose a framework that ameliorates this issue by performing scene reconstruction and semantic scene completion jointly in an incremental and real-time manner, based on an input sequence of depth maps.

3D Semantic Scene Completion

Distortion-Aware Convolutional Filters for Dense Prediction in Panoramic Images

no code implementations ECCV 2018 Keisuke Tateno, Nassir Navab, Federico Tombari

There is a high demand of 3D data for 360° panoramic images and videos, pushed by the growing availability on the market of specialized hardware for both capturing (e. g., omnidirectional cameras) as well as visualizing in 3D (e. g., head mounted displays) panoramic images and videos.

Semantic Segmentation Style Transfer

Peeking Behind Objects: Layered Depth Prediction from a Single Image

no code implementations23 Jul 2018 Helisa Dhamo, Keisuke Tateno, Iro Laina, Nassir Navab, Federico Tombari

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.

Depth Estimation Depth Prediction

Fast and Accurate Semantic Mapping through Geometric-based Incremental Segmentation

no code implementations7 Mar 2018 Yoshikatsu Nakajima, Keisuke Tateno, Federico Tombari, Hideo Saito

We propose an efficient and scalable method for incrementally building a dense, semantically annotated 3D map in real-time.

CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction

no code implementations CVPR 2017 Keisuke Tateno, Federico Tombari, Iro Laina, Nassir Navab

Given the recent advances in depth prediction from Convolutional Neural Networks (CNNs), this paper investigates how predicted depth maps from a deep neural network can be deployed for accurate and dense monocular reconstruction.

Depth Estimation Depth Prediction +1

Cannot find the paper you are looking for? You can Submit a new open access paper.