— We propose a novel approach to improve further the quality of recovered images from standard super-resolution reconstruction, using Lewitt’s Kaiser-Bessel window functions (b...
Current state-of-the-art image-based scene reconstruction
techniques are capable of generating high-fidelity 3D
models when used under controlled capture conditions.
However, th...
Jean-Yves Guillemaut, Joe Kilner and Adrian Hilton
While low-dimensional image representations have been very popular in computer vision, they suffer from two limitations: (i) they require collecting a large and varied training se...
Efficient algorithms for compressing geometric data have been widely developed in the recent years, but they are mainly designed for closed polyhedral surfaces which are manifold ...
We propose a new robust focal length estimation method in multi-view structure from motion from unordered data sets, e.g. downloaded from the Flickr database, where jpeg-exif heade...