Intrinsic Light Field Images
This work addresses a domain-specific problem for computer vision researchers and practitioners working with light field imaging, offering an incremental improvement by extending existing theory to handle higher-dimensional data.
The paper tackles the problem of decomposing a 4D light field into intrinsic shading and albedo components, which previous methods struggled with due to high dimensionality and lack of angular coherence. The proposed algorithm achieves 4D intrinsic decompositions that are difficult for state-of-the-art methods to match.
We present a method to automatically decompose a light field into its intrinsic shading and albedo components. Contrary to previous work targeted to 2D single images and videos, a light field is a 4D structure that captures non-integrated incoming radiance over a discrete angular domain. This higher dimensionality of the problem renders previous state-of-the-art algorithms impractical either due to their cost of processing a single 2D slice, or their inability to enforce proper coherence in additional dimensions. We propose a new decomposition algorithm that jointly optimizes the whole light field data for proper angular coherence. For efficiency, we extend Retinex theory, working on the gradient domain, where new albedo and occlusion terms are introduced. Results show our method provides 4D intrinsic decompositions difficult to achieve with previous state-of-the-art algorithms. We further provide a comprehensive analysis and comparisons with existing intrinsic image/video decomposition methods on light field images.