Selfies can often be misrepresentative and unflattering. Due to the camera's proximity, selfies render subjects' noses larger, ears smaller and foreheads more sloping. To tackle this issue, researchers at Princeton University in the US have unveiled a new method for transforming selfies.
The method can modify a person's face to look as though it were photographed from farther away, and also alter someone's apparent pose, as if the camera were placed higher, lower or at an angle.When superimposed, images adjusted in this manner can further be used to generate 3D head shots.
‘Although it is the age of the selfie, many people are unaware of how much these self-portraits do not really look like the person being photographed because the camera is way too close,’ said Ohad Fried, a PhD candidate at Princeton University.
‘Now that people can edit so many aspects of a photo right on their phones, we wanted to provide a quick way to edit faces that maintains realism,’ Fried said. The project is the first of its kind to address the fixing of self-portrait distortions owing to camera distance, the researchers said.
‘As humans, we have evolved to be very sensitive to subtle cues in other people's faces, so any artifacts or glitches in synthesised imagery tend to really jump out,’ said Adam Finkelstein, a professor at Princeton.
‘With this new method, we therefore had to make sure the photo modifications looked extremely realistic, and we were frankly surprised at the fidelity of the results we were able to obtain starting from just a single photo,’ he said.
Researchers began with a model for generating digital, 3D human heads. The model came from FaceWarehouse, a database of 150 people photographed in 20 different poses, compiled by researchers at Zhejiang University in China.
Then, a programme made by researchers at Carnegie Mellon University in the US, identified nearly six dozen reference points across someone's face, such as the corners of the eyes and top of the head when presented with a selfie.
The photo-editing method then adjusts the 3D head model so that it corresponds to the points detected on the face. ‘Now we had an underlying 3D model of the 2D selfie image,’ said Fried.
Modifying the selfie then proved straightforward. The selfie's coordinates for facial reference points needed to be updated to match those in the 3D image of a face, photographed either in a different pose or by a more distant camera. The 2D image underwent a warp to approximate a desired change in its virtual 3D orientation, and all within just a handful of seconds.