Generalized Image Acquisition and Analysis

Maximum Mipmaps for Fast, Accurate, and Scalable Dynamic Height Field Rendering

This paper presents a GPU-based, fast, and accurate dynamic height field rendering technique that scales well to large scale height fields. Current real-time rendering algorithms for dynamic height fields employ approximate ray-height field intersection methods, whereas accurate algorithms require pre-computation in the order of seconds to minutes and are thus not suitable for dynamic height field rendering. We alleviate this problem by using maximum mipmaps, a hierarchical data structure supporting accurate and efficient rendering while simultaneously lowering the pre-computation costs to negligible levels. Furthermore, maximum mipmaps allow for view-dependent level-of-detail rendering. In combination with hierarchical ray-stepping this results in an efficient intersection algorithm for large scale height fields.

Three-Dimensional Kaleidoscopic Imaging

Ilya Reshetouski, Alkhazur Manakov, Hans-Peter Seidel, and Ivo Ihrke
CVPR 2011 (oral)
  Abstract

  We introduce three-dimensional kaleidoscopic imaging, a promising alternative for recording multi-view imagery.
  The main limitation of multi-view reconstruction techniques is the limited number of views that are available from multi-camera systems, especially for dynamic scenes.
  Our new system is based on imaging an object inside a kaleidoscopic mirror system. We show that this approach can generate a large number of high-quality views well distributed over the hemisphere surrounding the object in a single shot. In comparison to existing multi-view systems, our method offers a number of advantages: it is possible to operate with a single camera, the individual views are perfectly synchronized, and they have the same radiometric and colorimetric properties.
  We describe the setup both theoretically, and provide methods for a practical implementation. Enabling interfacing to standard multi-view algorithms for further processing is an important goal of our techniques.

  Example of labeling process:

=> => => =>
Source image Silhouette image Chambers extraction Visual hull
estimation
Labeling of views

  Files

Paper [pdf]
Supplemental materials [pdf]
Presentation [ppt]
Labeling data example (with MatLab loader) [zip]
Labeling of the dynamic scene example: Input movie [mpg], Segmentation movie [mpg], Labeling movie [mpg]