3D reconstruction pipelines using structure-from-motion and multi-view stereo techniques are today able to reconstruct impressive, large-scale geometry models from images but do not yield textured results. Current texture creation methods are unable to handle the complexity and scale of these models. We therefore present the first comprehensive texturing framework for large-scale, real-world 3D reconstructions. Our method addresses most challenges occurring in such reconstructions: the large number of input images, their drastically varying properties such as image scale, (out-of-focus) blur, exposure variation, and occluders (e.g., moving plants or pedestrians). Using the proposed technique, we are able to texture datasets that are several orders of magnitude larger and far more challenging than shown in related work.

No abstract

When two people view the same event and later try to remember it together, what one person says affects what the other person reports. A model is presented which predicts that this memory conformity effect will be moderated, in different ways, by two components of social anxiety. People with higher fear of negative evaluation should be more influenced by their peers than others, but those with higher social anxiety related to avoiding social situations may be less influenced by their peers than others. Pairs of adolescent-aged participants took part in a face recognition study. For each trial one person responded and then the next person responded. The effect of what the first person said on the second person's response was measured; the size of the effect was moderated by the social anxiety measures as predicted by the model. This is the first study showing the relationship between social anxiety and memory suggestibility.

No abstract

Kopf et al. [2013]Ö ztireli and Gross [2015] DPID λ=1.0 DPID λ=0.5 Figure 1: Row 1: Input images with 0.5, 1.9, 2.7, and 4.6 megapixels respectively. Rows 2-5: Downscaled results with 128 pixels width. Our algorithm (DPID) preserves stars in Example 1, thin lines in Example 2, roof tiles in Example 3, and text, lines and notes in Example 4.