State-of-the-art methods for diminished reality propagate pixel information from a keyframe to subsequent frames for real-time inpainting. However, these approaches produce artifacts, if the scene geometry is not sufficiently planar. In this article, we present InpaintFusion, a new real-time method that extends inpainting to non-planar scenes by considering both color and depth information in the inpainting process. We use an RGB-D sensor for simultaneous localization and mapping, in order to both track the camera and obtain a surfel map in addition to RGB images. We use the RGB-D information in a cost function for both the color and the geometric appearance to derive a global optimization for simultaneous inpainting of color and depth. The inpainted depth is merged in a global map by depth fusion. For the final rendering, we project the map model into image space, where we can use it for effects such as relighting and stereo rendering of otherwise hidden structures. We demonstrate the capabilities of our method by comparing it to inpainting results with methods using planar geometric proxies.

We propose an algorithm for generating an unstructured lumigraph in real-time from an image stream. This problem has important applications in mixed reality, such as telepresence, interior design or as-built documentation. Unlike conventional texture optimization in structure from motion, our method must choose views from the input stream in a strictly incremental manner, since only a small number of views can be stored or transmitted. This requires formulating an online variant of the well-known view-planning problem, which must take into account what parts of the scene have already been seen and how the lumigraph sample distribution could improve in the future. We address this highly unconstrained problem by regularizing the scene structure using a regular grid structure. Upon the grid structure, we define a coverage metric describing how well the lumigraph samples cover the grid in terms of spatial and angular resolution, and we greedily keep incoming views if they improve the coverage. We evaluate the performance of our algorithm quantitatively and qualitatively on a variety of synthetic and real scenes, and demonstrate visually appealing results obtained at real-time frame rates (in the range of 3Hz-100Hz per incoming image, depending on configuration).

Drones allow exploring dangerous or impassable areas safely from a distant point of view. However, flight control from an egocentric view in narrow or constrained environments can be challenging. Arguably, an exocentric view would afford a better overview and, thus, more intuitive flight control of the drone. Unfortunately, such an exocentric view is unavailable when exploring indoor environments. This paper investigates the potential of drone-augmented human vision, i.e., of exploring the environment and controlling the drone indirectly from an exocentric viewpoint. If used with a see-through display, this approach can simulate X-ray vision to provide a natural view into an otherwise occluded environment. The user's view is synthesized from a three-dimensional reconstruction of the indoor environment using image-based rendering. This user interface is designed to reduce the cognitive load of the drone's flight control. The user can concentrate on the exploration of the inaccessible space, while flight control is largely delegated to the drone's autopilot system. We assess our system with a first experiment showing how drone-augmented human vision supports spatial understanding and improves natural interaction with the drone.