Shape Registration with Directional Data
This work addresses shape registration problems in computer vision and graphics, offering an incremental improvement over existing methods.
The paper tackles shape registration by proposing cost functions that incorporate both Euclidean and non-Euclidean data, such as unit vectors, to estimate rigid and non-rigid transformations for 2D contours and 3D surfaces. The results show that combining a point's position and unit normal vector in the cost function improves registration compared to state-of-the-art methods.
We propose several cost functions for registration of shapes encoded with Euclidean and/or non-Euclidean information (unit vectors). Our framework is assessed for estimation of both rigid and non-rigid transformations between the target and model shapes corresponding to 2D contours and 3D surfaces. The experimental results obtained confirm that using the combination of a point's position and unit normal vector in a cost function can enhance the registration results compared to state of the art methods.