Title:
|
A Human Shape-Motion Predictor with Deep Learning
|
Author:
|
Romero Mérida, Antonio
|
Other authors:
|
Universitat Politècnica de Catalunya. Departament de Ciències de la Computació; Alquézar Mancho, René; Moreno-Noguer, Francesc |
Abstract:
|
The objective of this work is to obtain an end-to-end solution which predicts human motion and shape from a given video by extracting its pose in the Wild. Given incomplete human motion sequences our goal is to predict and visualize the following frames of those sequences, with realistic human shape |
Subject(s):
|
-Àrees temàtiques de la UPC::Informàtica -Neural networks (Computer science) -Machine learning -Predictor Moviment Humà; Estimació Pose 3D; SMPL Model; Xarxes Neuronals Recurrents; Forma Humà Realista ; Pose; Forma -Human-Motion Prediction; 3D Pose Estimation; SMPL Model; Recurrent Neural networks; Realistic Human Shape; Pose; Shape -Xarxes neuronals (Informàtica) -Aprenentatge automàtic |
Rights:
|
|
Document type:
|
Research/Master Thesis |
Published by:
|
Universitat Politècnica de Catalunya
|
Share:
|
|