2 papers
cs.CV2019
Physical Cue based Depth-Sensing by Color Coding with Deaberration Network
Nao Mishima, Tatsuo Kozakaya, Akihisa Moriya +2
Color-coded aperture (CCA) methods can physically measure the depth of a scene given by physical cues from a single-shot image of a monocular camera. However, they are vulnerable t…
cs.CV2017
BiSeg: Simultaneous Instance Segmentation and Semantic Segmentation with Fully Convolutional Networks
Viet-Quoc Pham, Satoshi Ito, Tatsuo Kozakaya
We present a simple and effective framework for simultaneous semantic segmentation and instance segmentation with Fully Convolutional Networks (FCNs). The method, called BiSeg, pre…