In recent years, digital cameras have significantly increased in quality and resolution, while dropping prices make them available for many different applications. Current high resolution images now show many details of a scene that are otherwise difficult to capture, e.g. with scanners or other 3D sensors. In this talk, methods are presented that exploit multiple high resolution views for image-based analysis, modelling, and rendering of 3D scenes. A method for high-detail 3D geometry estimation is shown that exploits the visible details of material structures, like the skin for face reconstruction. While such approaches lead to detailed 3D models,
rendering of 3D scenes can also be conducted by exploiting detailed information from images or video. For combined geometry and image-based rendering of dynamic objects like human or faces, we show that approximate geometry is often sufficient for creating realistic representations that can be animated similar to classical approaches. Examples are given for applications with multi-media, digital cinema, video communication, and virtual reality.