A Generative Model for Generic Light Field Reconstruction
This work addresses the need for flexible and robust light field reconstruction methods in computer vision, though it is incremental as it builds on existing generative and optimization techniques.
The authors tackled the problem of limited applicability in learning-based light field reconstruction by introducing a generative model for 4D light field patches using variational autoencoders, which can be integrated as a prior into model-based optimization for tasks like view synthesis and super resolution, achieving performance close to end-to-end networks and outperforming traditional methods.
Recently deep generative models have achieved impressive progress in modeling the distribution of training data. In this work, we present for the first time a generative model for 4D light field patches using variational autoencoders to capture the data distribution of light field patches. We develop a generative model conditioned on the central view of the light field and incorporate this as a prior in an energy minimization framework to address diverse light field reconstruction tasks. While pure learning-based approaches do achieve excellent results on each instance of such a problem, their applicability is limited to the specific observation model they have been trained on. On the contrary, our trained light field generative model can be incorporated as a prior into any model-based optimization approach and therefore extend to diverse reconstruction tasks including light field view synthesis, spatial-angular super resolution and reconstruction from coded projections. Our proposed method demonstrates good reconstruction, with performance approaching end-to-end trained networks, while outperforming traditional model-based approaches on both synthetic and real scenes. Furthermore, we show that our approach enables reliable light field recovery despite distortions in the input.