Superresolution Reflectance Fields: Synthesizing images for intermediate light directions

Captured re ectance elds tend to provide a relatively 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 re ectance elds that reconstructs plausible images even for non-observed light directions. Given a sparsely sampled re ectance eld, we can effectively synthesize images as they would have been obtained from denser sampling. The processing pipeline consists of three steps: (1) segmentation of regions where intermediate lighting cannot be obtained by blending, (2) appropriate ow algorithms for highlights and shadows, plus (3) a nal reconstruction technique that uses image-based priors to faithfully correct errors that might be introduced by the segmentation or ow step. The algorithm reliably reproduces scenes that contain specular highlights, interre ections, shadows or caustics