The bounding box representation employed by many popular object detection models [3, 6] implicitly assumes all pixels inside the box belong to the object. This assumption makes th...
Surface registration is a fundamental step in the reconstruction of three-dimensional objects. While there are several fast and reliable methods to align two surfaces, the tools a...
Andrea Torsello, Emanuele Rodola, Andrea Albarelli
Image-based location estimation methods typically recognize every photo independently, and their resulting reliance on strong visual feature matches makes them most suited for dis...
This paper extends classical object pose and relative camera motion estimation algorithms for imaging sensors sampling the scene through light-paths. Many algorithms in multi-view...
Srikumar Ramalingam, Sofien Bouaziz, Peter Sturm, ...
In real-world applications, “what you saw” during training is often not “what you get” during deployment: the distribution and even the type and dimensionality of features...