Bayesian probability

Geology

Classification of discontinuities

Image warping

Prior probability

Mathematics

Algorithm

Image (mathematics)

Statistics

Extrapolation

Extreme value theory

Pixel

Mathematical analysis

Paleontology

Leverage (statistics)

Artificial intelligence

Rendering (computer graphics)

View synthesis

Context (archaeology)

Computer science

Computer vision

We present Extreme View Synthesis, a solution for novel view extrapolation that works even when the number of input images is small---as few as two. In this context, occlusions and depth uncertainty are two of the most pressing issues, and worsen as the degree of extrapolation increases. We follow the traditional paradigm of performing depth-based warping and refinement, with a few key improvements. First, we estimate a depth probability volume, rather than just a single depth value for each pixel of the novel view. This allows us to leverage depth uncertainty in challenging regions, such as depth discontinuities. After using it to get an initial estimate of the novel view, we explicitly combine learned image priors and the depth uncertainty to synthesize a refined image with less artifacts. Our method is the first to show visually pleasing results for baseline magnifications of up to 30x.

Extreme View Synthesis