Polarization Human Shape and Pose Dataset

04/30/2020
by   Shihao Zou, et al.
14

Polarization images are known to be able to capture polarized reflected lights that preserve rich geometric cues of an object, which has motivated its recent applications in reconstructing detailed surface normal of the objects of interest. Meanwhile, inspired by the recent breakthroughs in human shape estimation from a single color image, we attempt to investigate the new question of whether the geometric cues from polarization camera could be leveraged in estimating detailed human body shapes. This has led to the curation of Polarization Human Shape and Pose Dataset (PHSPD)5, our home-grown polarization image dataset of various human shapes and poses.

READ FULL TEXT

page 2

page 3

page 7

research
07/17/2020

3D Human Shape Reconstruction from a Polarization Image

This paper tackles the problem of estimating 3D body shape of clothed hu...
research
08/03/2016

Detailed Garment Recovery from a Single-View Image

Most recent garment capturing techniques rely on acquiring multiple view...
research
02/21/2014

Ergonomic-driven Geometric Exploration and Reshaping

The paper addresses the following problem: given a set of man-made shape...
research
07/05/2021

Towards Better Adversarial Synthesis of Human Images from Text

This paper proposes an approach that generates multiple 3D human meshes ...
research
07/22/2013

A Novel Equation based Classifier for Detecting Human in Images

Shape based classification is one of the most challenging tasks in the f...
research
10/01/2014

Coupling Top-down and Bottom-up Methods for 3D Human Pose and Shape Estimation from Monocular Image Sequences

Until recently Intelligence, Surveillance, and Reconnaissance (ISR) focu...
research
11/28/2022

In-Hand 3D Object Scanning from an RGB Sequence

We propose a method for in-hand 3D scanning of an unknown object from a ...

Please sign up or login with your details

Forgot password? Click here to reset