Our work was inspired by recent advances in image segmentation where flux-based functionals significantly improved alignment of object boundaries. We propose a novel photoflux functional for multi-view 3D reconstruction that is closely related to properties of photohulls. Our photohull prior can be combined with regularization. Thus, this work unifies two major groups of multiview stereo techniques: "space carving" and "deformable models". Our approach combines benefits of both groups and allows to recover fine shape details without oversmoothing while robustly handling noise. Photoflux provides data-driven ballooning force that helps to segment thin structures or holes. Photoflux maximizing shapes can be also seen as regularized Lapla-cian zero-crossings . We discuss several versions of photoflux functional based on global, local, or non-deterministic visibility models. Some forms of photoflux can be easily added into standard regularization techniques. For other forms we propose new optimization methods.
|Number of pages||10|
|Publication status||Published - 2006|
|Event||2006 17th British Machine Vision Conference, BMVC 2006 - Edinburgh, United Kingdom|
Duration: 4 Sep 2006 → 7 Sep 2006
|Conference||2006 17th British Machine Vision Conference, BMVC 2006|
|Period||4/09/06 → 7/09/06|