Automatic Face Aging in Videos via Deep Reinforcement Learning

TL;DR

This paper introduces a deep reinforcement learning method for automatically synthesizing age-progressed facial videos that maintain identity and temporal consistency, outperforming previous single-image approaches.

Contribution

The novel approach models face aging in videos using deep reinforcement learning, ensuring identity preservation and temporal smoothness across frames.

Findings

Enhanced quality of age-progressed faces in videos

Improved temporal consistency and smoothness

Better cross-age face verification results

Abstract

This paper presents a novel approach to synthesize automatically age-progressed facial images in video sequences using Deep Reinforcement Learning. The proposed method models facial structures and the longitudinal face-aging process of given subjects coherently across video frames. The approach is optimized using a long-term reward, Reinforcement Learning function with deep feature extraction from Deep Convolutional Neural Network. Unlike previous age-progression methods that are only able to synthesize an aged likeness of a face from a single input image, the proposed approach is capable of age-progressing facial likenesses in videos with consistently synthesized facial features across frames. In addition, the deep reinforcement learning method guarantees preservation of the visual identity of input faces after age-progression. Results on videos of our new collected aging face AGFW-v2 database demonstrate the advantages of the proposed solution in terms of both quality of age-progressed faces, temporal smoothness, and cross-age face verification.