Stratified Labeling for Surface Consistent Parallax Correction and Occlusion Completion
This addresses the challenge of reliable novel view synthesis in light field imaging for applications like virtual reality or computational photography, representing a strong specific gain rather than a foundational advance.
The paper tackles the problem of synthesizing high-quality novel light field views far beyond the angular baselines of given references, achieving over 3dB quality improvement against state-of-the-art methods.
The light field faithfully records the spatial and angular configurations of the scene, which facilitates a wide range of imaging possibilities. In this work, we propose an LF synthesis algorithm which renders high quality novel LF views far outside the range of angular baselines of the given references. A stratified synthesis strategy is adopted which parses the scene content based on stratified disparity layers and across a varying range of spatial granularities. Such a stratified methodology proves to help preserve scene structures over large perspective shifts, and it provides informative clues for inferring the textures of occluded regions. A generative-adversarial network model is further adopted for parallax correction and occlusion completion conditioned on the stratified synthesis features. Experiments show that our proposed model can provide more reliable novel view synthesis quality at large baseline extension ratios. Over 3dB quality improvement has been achieved against state-of-the-art LF view synthesis algorithms.