Photo Wake-Up: 3D Character Animation from a Single Photo
C. Weng, B. Curless, и I. Kemelmacher-Shlizerman. (2018)cite arxiv:1812.02246Comment: The project page is at https://grail.cs.washington.edu/projects/wakeup/, and the supplementary video is at https://youtu.be/G63goXc5MyU.
Аннотация
We present a method and application for animating a human subject from a
single photo. E.g., the character can walk out, run, sit, or jump in 3D. The
key contributions of this paper are: 1) an application of viewing and animating
humans in single photos in 3D, 2) a novel 2D warping method to deform a posable
template body model to fit the person's complex silhouette to create an
animatable mesh, and 3) a method for handling partial self occlusions. We
compare to state-of-the-art related methods and evaluate results with human
studies. Further, we present an interactive interface that allows re-posing the
person in 3D, and an augmented reality setup where the animated 3D person can
emerge from the photo into the real world. We demonstrate the method on photos,
posters, and art.
Описание
[1812.02246] Photo Wake-Up: 3D Character Animation from a Single Photo
cite arxiv:1812.02246Comment: The project page is at https://grail.cs.washington.edu/projects/wakeup/, and the supplementary video is at https://youtu.be/G63goXc5MyU
%0 Generic
%1 weng2018photo
%A Weng, Chung-Yi
%A Curless, Brian
%A Kemelmacher-Shlizerman, Ira
%D 2018
%K 2018 3D animation arxiv deep-learning paper uw
%T Photo Wake-Up: 3D Character Animation from a Single Photo
%U http://arxiv.org/abs/1812.02246
%X We present a method and application for animating a human subject from a
single photo. E.g., the character can walk out, run, sit, or jump in 3D. The
key contributions of this paper are: 1) an application of viewing and animating
humans in single photos in 3D, 2) a novel 2D warping method to deform a posable
template body model to fit the person's complex silhouette to create an
animatable mesh, and 3) a method for handling partial self occlusions. We
compare to state-of-the-art related methods and evaluate results with human
studies. Further, we present an interactive interface that allows re-posing the
person in 3D, and an augmented reality setup where the animated 3D person can
emerge from the photo into the real world. We demonstrate the method on photos,
posters, and art.
@misc{weng2018photo,
abstract = {We present a method and application for animating a human subject from a
single photo. E.g., the character can walk out, run, sit, or jump in 3D. The
key contributions of this paper are: 1) an application of viewing and animating
humans in single photos in 3D, 2) a novel 2D warping method to deform a posable
template body model to fit the person's complex silhouette to create an
animatable mesh, and 3) a method for handling partial self occlusions. We
compare to state-of-the-art related methods and evaluate results with human
studies. Further, we present an interactive interface that allows re-posing the
person in 3D, and an augmented reality setup where the animated 3D person can
emerge from the photo into the real world. We demonstrate the method on photos,
posters, and art.},
added-at = {2019-01-19T09:16:12.000+0100},
author = {Weng, Chung-Yi and Curless, Brian and Kemelmacher-Shlizerman, Ira},
biburl = {https://www.bibsonomy.org/bibtex/22ed2e5e5d093e4d872b3919aef82d0b2/analyst},
description = {[1812.02246] Photo Wake-Up: 3D Character Animation from a Single Photo},
interhash = {7688e994da546be72240092908147cc0},
intrahash = {2ed2e5e5d093e4d872b3919aef82d0b2},
keywords = {2018 3D animation arxiv deep-learning paper uw},
note = {cite arxiv:1812.02246Comment: The project page is at https://grail.cs.washington.edu/projects/wakeup/, and the supplementary video is at https://youtu.be/G63goXc5MyU},
timestamp = {2019-01-19T09:16:12.000+0100},
title = {Photo Wake-Up: 3D Character Animation from a Single Photo},
url = {http://arxiv.org/abs/1812.02246},
year = 2018
}