Visual Comfort Aware-Reinforcement Learning for Depth Adjustment of Stereoscopic 3D Images
This work addresses visual comfort and depth perception issues for users of stereoscopic 3D images, representing an incremental improvement by applying existing reinforcement learning methods to a specific domain task.
The paper tackled the problem of enhancing visual experience in stereoscopic 3D images by automating depth adjustment, using a deep reinforcement learning approach that models human sequential decision-making, and demonstrated effectiveness through experiments and user studies on three databases.
Depth adjustment aims to enhance the visual experience of stereoscopic 3D (S3D) images, which accompanied with improving visual comfort and depth perception. For a human expert, the depth adjustment procedure is a sequence of iterative decision making. The human expert iteratively adjusts the depth until he is satisfied with the both levels of visual comfort and the perceived depth. In this work, we present a novel deep reinforcement learning (DRL)-based approach for depth adjustment named VCA-RL (Visual Comfort Aware Reinforcement Learning) to explicitly model human sequential decision making in depth editing operations. We formulate the depth adjustment process as a Markov decision process where actions are defined as camera movement operations to control the distance between the left and right cameras. Our agent is trained based on the guidance of an objective visual comfort assessment metric to learn the optimal sequence of camera movement actions in terms of perceptual aspects in stereoscopic viewing. With extensive experiments and user studies, we show the effectiveness of our VCA-RL model on three different S3D databases.