Distortion-Free Wide-Angle Portrait on Camera Phone
Abstract
Photographers take wide-angle shots to enjoy expanding views, group portraits that never miss anyone, or extra freedoms to composite subjects with spectacular scenery background. In spite of the rapid proliferation of wide-angle camera on mobile phones, a wider field-of-view (FOV) introduces a stronger perspective distortion.
Most notably, portrait subjects may look vastly different from real-life, such as that the faces are stretched, squished, and skewed. Correcting such distortions requires professional editing skills, as trivial manipulations can introduce other kinds of distortions.
This paper introduces a new algorithm to recover undistorted faces without disturbing other parts of the photo. Motivated by that the stereographic projection preserves local geometry from the camera viewing sphere, we formulate an optimization problem to create a warping mesh, which locally adapts to the stereographic projection on facial regions,, and seamlessly evolves to the perspective projection over the background. We introduce a new energy function to minimize face distortions, which works reliably even for a large group selfie. We also use a CNN-based portrait segmentation to assign the weights in the objective function. Our algorithm is fully automatic and runs at an interactive rate on the mobile platform. We demonstrate promising results on a wide-range of camera FOVs from 72-115\degree.
Most notably, portrait subjects may look vastly different from real-life, such as that the faces are stretched, squished, and skewed. Correcting such distortions requires professional editing skills, as trivial manipulations can introduce other kinds of distortions.
This paper introduces a new algorithm to recover undistorted faces without disturbing other parts of the photo. Motivated by that the stereographic projection preserves local geometry from the camera viewing sphere, we formulate an optimization problem to create a warping mesh, which locally adapts to the stereographic projection on facial regions,, and seamlessly evolves to the perspective projection over the background. We introduce a new energy function to minimize face distortions, which works reliably even for a large group selfie. We also use a CNN-based portrait segmentation to assign the weights in the objective function. Our algorithm is fully automatic and runs at an interactive rate on the mobile platform. We demonstrate promising results on a wide-range of camera FOVs from 72-115\degree.
Research Areas
