Depth annotations: Designing depth of a single image for depth-based effects

Abstract

We present a novel pipeline to generate a depth map from a single image that can be used as input for a variety of artistic depth-based effects. In such a context, the depth maps do not have to be perfect but are rather designed with respect to a desired result. Consequently, our solution centers around user interaction and relies on a scribble-based depth editing. The annotations can be sparse, as the depth map is generated by a diffusion process, which is guided by image features. We support a variety of controls, such as a non-linear depth mapping, a steering mechanism for the diffusion (e.g., directionality, emphasis, or reduction of the influence of image cues), and besides absolute, we also support relative depth indications. In case that a depth estimate is available from an automatic solution, we illustrate how this information can be integrated in form of a depth palette, that allows the user to transfer depth values via a painting metaphor. We demonstrate a variety of artistic 3D results, including wiggle stereoscopy, artistic abstractions, haze, unsharp masking, and depth of field.