Superresolution Reflectance Fields: Synthesizing images for intermediate light directions

Captured reflectance fields provide in most cases a rather coarse sampling of the incident light directions. As a result, sharp illumination features, such as highlights or shadow boundaries, are poorly reconstructed during relighting; highlights are disconnected, and shadows show banding artefacts. In this paper, we propose a novel interpolation technique for 4D reflectance fields that is capable of reconstructing plausible images even for nonobserved light directions. Given a sparsely sampled reflectance field, we can effectively synthesize images as they would have been obtained from denser sampling. The processing pipeline consists of three steps: segmentation of regions where apparent motion cannot be obtained by blending, appropriate flow algorithms for highlights and shadows, plus a final reconstruction technique that uses image-based priors to faithfully correct errors that might be introduced by the segmentation or flow step. The algorithm reliably reproduces scenes containing specular highlights, interreflections, shadows or caustics.