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.@en

We propose a novel framework for photometric stereo (PS) under low-light conditions using uncalibrated near-light illumination. It operates on free-form video sequences captured with a minimalistic and affordable setup. We address issues such as albedo variations, shadowing, perspective projections, and camera noise. Our method uses specular spheres detected with a perspective-correcting Hough transform to robustly triangulate light positions in the presence of outliers via a least-squares approach. Furthermore, we propose an iterative reweighting scheme in combination with an ℓp-norm minimizer to robustly solve the calibrated near-light PS problem. In contrast to other approaches, our framework reconstructs depth, albedo (relative to light source intensity), and normals simultaneously and is demonstrated on synthetic and real-world scenes.@en

Depth plays an essential role in computer graphics for the sorting of primitives. The related data representation, the depth map, is useful for many different applications. In this dissertation, we present solutions for creating depth maps with the goal of using these maps to enhance the depth perception in the original images. Regarding the generation of depth maps, we propose two solutions, a reconstruction method via near-light photometric stereo (PS) and a depth map design tool via user guidance. Additionally, we present several techniques for image enhancement of depth perception based on depth information. In the following, we give a short summary of the dissertation.@en

Split-depth images use an optical illusion, which can enhance the 3D impression of a 2D animation. In split-depth images (also often called split-depth GIFs due to the commonly used file format), static virtual occluders inform of vertical or horizontal bars are added to a video clip, which leads to occlusions that are interpreted by the observer as a depth cue. In this paper, we study different factors that contribute to the illusion and propose a solution to generate split-depth images for a given RGB + depth image sequence. The presented solution builds upon a motion summarization of the object of interest (OOI) through space and time. It allows us to formulate the bar positioning as an energy-minimization problem, which we solve efficiently. We take a variety of important features into account, such as the changes of the 3D effect due to changes in the motion topology, occlusion, the proximity of bars or the OOI, and scene saliency. We conducted a number of psycho-visual experiments to derive an appropriate energy formulation. Our method helps in finding optimal positions for the bars and, thus, improves the 3D perception of the original animation. We demonstrate the effectiveness of our approach on a variety of examples. Our study with novice users shows that our approach allows them to quickly create satisfying results even for complex animations. @en

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. Additionally, 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. We demonstrate a variety of artistic 3D results, including wiggle stereoscopy and depth of field.@en