Unsupervised person image synthesis in arbitrary poses
Cita com:
hdl:2117/129790
Tipus de documentText en actes de congrés
Data publicació2018
EditorInstitute of Electrical and Electronics Engineers (IEEE)
Condicions d'accésAccés obert
Llevat que s'hi indiqui el contrari, els
continguts d'aquesta obra estan subjectes a la llicència de Creative Commons
:
Reconeixement-NoComercial-SenseObraDerivada 3.0 Espanya
ProjecteAEROARMS - AErial RObotic system integrating multiple ARMS and advanced manipulation capabilities for inspection and maintenance (EC-H2020-644271)
ENTENDER EL MOVIMIENTO HUMANO PARA ADAPTAR EL COMPORTAMIENTO DE UN ROBOT (AEI-TIN2017-90086-R)
ENTENDER EL MOVIMIENTO HUMANO PARA ADAPTAR EL COMPORTAMIENTO DE UN ROBOT (AEI-TIN2017-90086-R)
Abstract
We present a novel approach for synthesizing photo-realistic images of people in arbitrary poses using generative adversarial learning. Given an input image of a person and a desired pose represented by a 2D skeleton, our model renders the image of the same person under the new pose, synthesizing novel views of the parts visible in the input image and hallucinating those that are not seen. This problem has recently been addressed in a supervised manner, i.e., during training the ground truth images under the new poses are given to the network. We go beyond these approaches by proposing a fully unsupervised strategy. We tackle this challenging scenario by splitting the problem into two principal subtasks. First, we consider a pose conditioned bidirectional generator that maps back the initially rendered image to the original pose, hence being directly comparable to the input image without the need to resort to any training image. Second, we devise a novel loss function that incorporates content and style terms, and aims at producing images of high perceptual quality. Extensive experiments conducted on the DeepFashion dataset demonstrate that the images rendered by our model are very close in appearance to those obtained by fully supervised approaches.
Descripció
© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
CitacióPumarola, A. [et al.]. Unsupervised person image synthesis in arbitrary poses. A: IEEE Conference on Computer Vision and Pattern Recognition. "2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition". Institute of Electrical and Electronics Engineers (IEEE), 2018, p. 8620-8628.
Versió de l'editorhttps://ieeexplore.ieee.org/document/8578997
Col·leccions
- IRI - Institut de Robòtica i Informàtica Industrial, CSIC-UPC - Ponències/Comunicacions de congressos [576]
- Departament d'Enginyeria de Sistemes, Automàtica i Informàtica Industrial - Ponències/Comunicacions de congressos [1.500]
- VIS - Visió Artificial i Sistemes Intel·ligents - Ponències/Comunicacions de congressos [292]
- ROBiri - Grup de Percepció i Manipulació Robotitzada de l'IRI - Ponències/Comunicacions de congressos [252]
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
2024-Unsupervis ... sis-in-arbitrary-poses.pdf | 3,106Mb | Visualitza/Obre |