Loading...

Latent 3D Volume for Joint Depth Estimation and Semantic Segmentation from a Single Image

This paper proposes a novel 3D representation, namely, a latent 3D volume, for joint depth estimation and semantic segmentation. Most previous studies encoded an input scene (typically given as a 2D image) into a set of feature vectors arranged over a 2D plane. However, considering the real world is...

Full description

Saved in:
Bibliographic Details
Published in:Sensors (Basel)
Main Authors: Ito, Seiya, Kaneko, Naoshi, Sumi, Kazuhiko
Format: Artigo
Language:Inglês
Published: MDPI 2020
Subjects:
Online Access:https://ncbi.nlm.nih.gov/pmc/articles/PMC7601744/
https://ncbi.nlm.nih.gov/pubmed/33053692
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.3390/s20205765
Tags: Add Tag
No Tags, Be the first to tag this record!