Name: Ji Hou (侯骥)
Position: Ph.D Candidate
E-Mail: ji.hou@tum.de
Phone: +49-89-289-19595
Room No: 02.13.35

Bio

I'm a first-year Ph.D Candidate at the Visual Computing Lab headed by Prof. Matthias Nießner. I received my Master's degree in Computer Science in RWTH Aachen University. Currently, my research focus on 3D Scene Understanding.

Research Interest

  • Computer Vision and Deep Learning
  • 3D Scene Understanding
  • Conditional Generative Models

Publications

2019

3D-SIC: 3D Semantic Instance Segmentation for RGB-D Scans
Ji Hou, Angela Dai, Matthias Nießner
arXiv 2019
This paper introduces the task of semantic instance completion: from an incomplete, RGB-D scan of a scene, we detect the individual object instances comprising the scene and jointly infer their complete object geometry.
[bibtex][project page]

3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans
Ji Hou, Angela Dai, Matthias Nießner
CVPR 2019 (Oral)
We introduce 3D-SIS, a novel neural network architecture for 3D semantic instance segmentation in commodity RGB-D scans.
[video][code][bibtex][project page]