Towards Automatic Image Editing: Learning to See another You

Xu Jia, Amir Ghodrati, Marco Pedersoli and Tinne Tuytelaars

Abstract

In this paper we propose a method that aims at automatically editing an image by altering its attributes. More specifically, given an image of a certain class (e.g. a human face), the method should generate a new image as similar as possible to the given one, but with an altered visual attribute (e.g. the same face with a new pose or a different illumination). To this end, we propose a solution following an encoder-decoder pipeline. The desired attribute and the input image are independently encoded into a convolutional network and fused at feature map level. A convolutional decoder is then used to generate the target image. The result is further refined with another convolutional encoder-decoder network with the initial result and the original image as inputs. We evaluate the proposed method on MultiPIE dataset for three sub-tasks, that is, rotating faces, changing illumination and image inpainting. We show that the method is able to generate realistic images for the three tasks in most of the evaluated samples.

Session

Posters 2

Files

Extended Abstract (PDF, 1M)
Paper (PDF, 1M)

DOI

10.5244/C.30.101
https://dx.doi.org/10.5244/C.30.101

Citation

Bibtex

        @inproceedings{BMVC2016_101,
        	title={Towards Automatic Image Editing: Learning to See another You},
        	author={Xu Jia, Amir Ghodrati, Marco Pedersoli and Tinne Tuytelaars},
        	year={2016},
        	month={September},
        	pages={101.1-101.11},
        	articleno={101},
        	numpages={11},
        	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
        	publisher={BMVA Press},
        	editor={Richard C. Wilson, Edwin R. Hancock and William A. P. Smith},
        	doi={10.5244/C.30.101},
        	isbn={1-901725-59-6},
        	url={https://dx.doi.org/10.5244/C.30.101}
        }