Learning to Reconstruct People in Clothing from a Single RGB Camera
We present a learning-based model to infer the personalized 3D shape of people from a few frames (1-8) of a monocular video in which the person is moving, in less than 10 seconds with a reconstruction accuracy of 5mm. Our model learns to predict the parameters of a statistical body model and instance displacements that add clothing and hair to the shape. The model achieves fast and accurate predictions based on two key design choices. First, by predicting shape in a canonical T-pose space, the network learns to encode the images of the person into pose-invariant latent codes, where the information is fused. Second, based on the observation that feed-forward predictions are fast but do not always align with the input images, we predict using both, bottom-up and top-down streams (one per view) allowing information to flow in both directions. Learning relies only on synthetic 3D data. Once learned, the model can take a variable number of frames as input, and is able to reconstruct shapes even from a single image with an accuracy of 6mm. Results on 3 different datasets demonstrate the efficacy and accuracy of our approach.
NurtureToken New!

Token crowdsale for this paper ends in

Buy Nurture Tokens

Authors

Are you an author of this paper? Check the Twitter handle we have for you is correct.

Thiemo Alldieck (add twitter)
Marcus Magnor (add twitter)
Bharat Lal Bhatnagar (add twitter)
Christian Theobalt (add twitter)
Gerard Pons-Moll (add twitter)
Ask The Authors

Ask the authors of this paper a question or leave a comment.

Read it. Rate it.
#1. Which part of the paper did you read?

#2. The paper contains new data or analyses that is openly accessible?
#3. The conclusion is supported by the data and analyses?
#4. The conclusion is of scientific interest?
#5. The result is likely to lead to future research?

Github
User:
None (add)
Repo:
None (add)
Stargazers:
0
Forks:
0
Open Issues:
0
Network:
0
Subscribers:
0
Language:
None
Youtube
Link:
None (add)
Views:
0
Likes:
0
Dislikes:
0
Favorites:
0
Comments:
0
Other
Sample Sizes (N=):
Inserted:
Words Total:
Words Unique:
Source:
Abstract:
None
03/14/19 06:03PM
8,960
2,761
Tweets
aiton5: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
arxiv_cscv: Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/ETIm6feovf
thmo_a: The Octopus model from our #CVPR2019 paper "Learning to Reconstruct People in Clothing from a Single RGB Camera" is finally available: https://t.co/7RfCcWycLG Pre-print: https://t.co/hPG6mKq0IQ https://t.co/ONmX3ktjKp
arxiv_pop: 2019/03/14 投稿 2位 CV(Computer Vision and Pattern Recognition) Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/aUSULShOud 14 Tweets 49 Retweets 166 Favorites
seishin55: 「画像から3Dで人間を表現する」が盛り上がってきてる感。 - Learning to Reconstruct People in Clothing from a Single RGB Camera (14 Mar 2019) https://t.co/Zrj1IzmM93 - DeepHuman: 3D Human Reconstruction from a Single Image (15 Mar 2019) https://t.co/fJVBAV60Ox
chrisemoody: RT @arxiv_cscv: Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/ETIm6eWNDH
arxiv_cscv: Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/ETIm6eWNDH
jastner109: RT @arxiv_cscv: Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/ETIm6eWNDH
arxiv_cscv: Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/ETIm6eWNDH
arxiv_cscv: Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/ETIm6eWNDH
ProjectX_iOS: RT @pretendsmarts: The day I publish a new paper comes out (https://t.co/ZJZXzs5W7q) and I already had to postpone it by two days because o…
Game_DevBot: RT @pretendsmarts: The day I publish a new paper comes out (https://t.co/ZJZXzs5W7q) and I already had to postpone it by two days because o…
pretendsmarts: The day I publish a new paper comes out (https://t.co/ZJZXzs5W7q) and I already had to postpone it by two days because of @oculus Codec Avatars story. I'm pretty sure something new comes up during @Official_GDC from @Unity3dLabs or @Allegorithmic #gamedev #MachineLearning https://t.co/FBdzG79Kr9
omitawo: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
arxiv_cscv: Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/ETIm6eWNDH
sotongshi: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
fox_aki310ooooo: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
goodstoriez: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
sz_dr: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
amznzma: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
rkakamilan: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
arxiv_cscv: Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/ETIm6eWNDH
udoooom: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
nil_and_lin: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
arxivml: "Learning to Reconstruct People in Clothing from a Single RGB Camera", Thiemo Alldieck, Marcus Magnor, Bharat Lal B… https://t.co/OEckT4YkTE
moto_josyu_K: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
khmlpy: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
kuz44ma69: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
DanielP75506024: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
asymmeto: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
h_tee: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
N3uuSp3ak: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
morioka: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
Hako_matsu: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
thmo_a: The pre-print of our #cvpr2019 work "Learning to Reconstruct People in Clothing from a Single RGB Camera" is now available on #arxiv: https://t.co/hPG6mKq0IQ We present a learning-based model to infer the personalized 3D shape of people from only a few monocular video frames.
higashikyou: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
shikihuton: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
ComputerPapers: Learning to Reconstruct People in Clothing from a Single RGB Camera. https://t.co/8W61mDs90h
eagleutkk: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
tri_man: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
haruo31: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
dicekicker: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
SythonUK: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
Matteasu: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
QZTWE: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
yshhrknmr: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
jonma: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
nick_debu_p: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
shion_honda: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
shunk031: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
doiken23: RT @udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDS…
udoooom: こんな殺されそうな論文初めて見た Learning to Reconstruct People in Clothing from a Single RGB Camera https://t.co/1LFcHqah5Y https://t.co/vkDSOUFEdo
Images
Related