Non-Rigid Registration meets Surface Reconstruction

Mohammad Rouhani 1 Edmond Boyer 1 Angel D. Sappa 2
1 MORPHEO - Capture and Analysis of Shapes in Motion
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Non rigid registration is an important task in computer vision with many applications in shape and motion modeling. A fundamental step of the registration is the data association between the source and the target under consideration. Such association proves difficult in practice, due to the discrete nature of the information and its corruption by various types of noise, e.g. outliers and missing data. In this paper we investigate the benefit of the implicit representation multi-level Partition of Unity (MPU) for the registration of 3D point clouds from coarse to fine resolutions. Using this flexible surface representation, the discrete association between the source and the target can be replaced by a continuous distance field induced by this implicit interface. This significantly eases the registration by avoiding direct association between points. Moreover, by combining this distance field with a proper deformation term, the registration energy can be expressed in a linear least square form that is easy and fast to solve. Experimental results are provided for point clouds from multi-view data sets. The qualitative and quantitative comparisons show the outperformance and robustness of our framework in presence of noise and outliers.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/hal-01063513
Contributor : Mohammad Rouhani <>
Submitted on : Monday, September 15, 2014 - 1:40:45 PM
Last modification on : Monday, April 9, 2018 - 12:22:28 PM
Long-term archiving on: Tuesday, December 16, 2014 - 10:21:26 AM

File

3DV_final.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01063513, version 1

Citation

Mohammad Rouhani, Edmond Boyer, Angel D. Sappa. Non-Rigid Registration meets Surface Reconstruction. 3DV 2014 - International Conference on 3D Vision, Dec 2014, Tokyo, Japan. ⟨hal-01063513v1⟩

Share

Metrics

Record views

159

Files downloads

145