We present YouTouch!, a system that tracks users in front of an interactive display wall and associates touches with users. With their large size, display walls are inherently suitable for multi-user interaction. However, current touch recognition technology does not distinguish between users, making it hard to provide personalized user interfaces or access to private data. In our system we place a commodity RGB + depth camera in front of the wall, allowing us to track users and correlate them with touch events. While the camera's driver is able to track people, it loses the user's ID whenever she is occluded or leaves the scene. In these cases, we re-identify the person by means of a descriptor comprised of color histograms of body parts and skeleton-based biometric measurements. Additional processing reliably handles short-term occlusion as well as assignment of touches to occluded users. YouTouch! requires no user instrumentation nor custom hardware, and there is no registration nor learning phase. Our system was thoroughly tested with data sets comprising 81 people, demonstrating its ability to re-identify users and correlate them to touches even under adverse conditions.

Motion blur can adversely affect a number of vision tasks, hence it is generally considered a nuisance. We instead treat motion blur as a useful signal that allows to compute the motion of objects from a single image. Drawing on the success of joint segmentation and parametric motion models in the context of optical flow estimation, we propose a parametric object motion model combined with a segmentation mask to exploit localized, non-uniform motion blur. Our parametric image formation model is differentiable w.r.t. the motion parameters, which enables us to generalize marginal-likelihood techniques from uniform blind deblurring to localized, non-uniform blur. A two-stage pipeline, first in derivative space and then in image space, allows to estimate both parametric object motion as well as a motion segmentation from a single image alone. Our experiments demonstrate its ability to cope with very challenging cases of object motion blur.

Defocus blur is an indicator for the depth structure of a scene. However, given a single input image from a conventional camera one cannot distinguish between blurred objects lying in front or behind the focal plane, as they may be subject to exactly the same amount of blur. In this paper we address this limitation by exploiting coded apertures. Previous work in this area focuses on setups where the scene is placed either entirely in front or entirely behind the focal plane. We demonstrate that asymmetric apertures result in unique blurs for all distances from the camera. To exploit asymmetric apertures we propose an algorithm that can unambiguously estimate scene depth and texture from a single input image. One of the main advantages of our method is that, within the same depth range, we can work with less blurred data than in other methods. The technique is tested on both synthetic and real images.

Traditional optical flow algorithms rely on consecutive short-exposed images. In this work, we make use of an additional long-exposed image for motion field estimation. Long-exposed images integrate motion information directly in the form of motion-blur. With this additional information, more robust and accurate motion fields can be estimated. In addition, the moment of occlusion can be determined. Considering the basic signal-theoretical problem in motion field estimation, we exploit the fact that long-exposed images integrate motion information to prevent temporal aliasing. A suitable image formation model relates the long-exposed image to preceding and succeeding short-exposed images in terms of dense 2D motion and per-pixel occlusion/disocclusion timings. Based on our image formation model, we describe a practical variational algorithm to estimate the motion field not only for visible image regions but also for regions getting occluded. Results for synthetic as well as real-world scenes demonstrate the validity of the approach.

Video editing plays an important role in today's cinematic post-production: editing operations are typically applied on a keyframe basis and propagated automatically to the rest of the sequence. Thereby, small inconsistencies in correspondences used for the propagation of editing operations accumulate and need to be corrected manually. The amount of required manual interaction increases further when editing stereoscopic video sequences. In this paper, we propose an algorithm for looped correspondence estimation yielding consistent correspondences that can be used for reliable propagation of editing operations along a stereoscopic video sequence, avoiding drift and error accumulation common to standard approaches. Taking an additional spatially adjacent image into account, we extend standard two-image optical flow algorithms and exploit data redundancy within stereoscopic video sequences. Our proposed algorithm not only yields robust and consistent correspondences for stereo footage, but also improves the accuracy of standard two-image motion estimation as demonstrated for several test scenes with known ground truth.

Abstract We present an image‐based rendering system to viewpoint‐navigate through space and time of complex real‐world, dynamic scenes. Our approach accepts unsynchronized, uncalibrated multivideo footage as input. Inexpensive, consumer‐grade camcorders suffice to acquire arbitrary scenes, for example in the outdoors, without elaborate recording setup procedures, allowing also for hand‐held recordings. Instead of scene depth estimation, layer segmentation or 3D reconstruction, our approach is based on dense image correspondences, treating view interpolation uniformly in space and time: spatial viewpoint navigation, slow motion or freeze‐and‐rotate effects can all be created in the same way. Acquisition simplification, integration of moving cameras, generalization to difficult scenes and space–time symmetric interpolation amount to a widely applicable virtual video camera system.

Abstract We present a novel multi‐view, projective texture mapping technique. While previous multi‐view texturing approaches lead to blurring and ghosting artefacts if 3D geometry and/or camera calibration are imprecise, we propose a texturing algorithm that warps (“floats”) projected textures during run‐time to preserve crisp, detailed texture appearance. Our GPU implementation achieves interactive to real‐time frame rates. The method is very generally applicable and can be used in combination with many image‐based rendering methods or projective texturing applications. By using Floating Textures in conjunction with, e.g., visual hull rendering, light field rendering, or free‐viewpoint video, improved rendering results are obtained from fewer input images, less accurately calibrated cameras, and coarser 3D geometry proxies.