Abstract
Shape registration is fundamental to 3D object acquisition; it is used to fuse scans from multiple views. Existing algorithms mainly utilize geometric information to determine alignment, but this typically results in noticeable misalignment of textures (i.e. surface colors) when using RGB-depth cameras. We address this problem using a novel approach to color-aware registration, which takes both color and geometry into consideration simultaneously. Color information is exploited throughout the pipeline to provide more effective sampling, correspondence and alignment, in particular for surfaces with detailed textures. Our method can furthermore tackle both rigid and non-rigid registration problems (arising, for example, due to small changes in the object during scanning, or camera distortions). We demonstrate that our approach produces significantly better results than previous methods.
Highlights
Reconstructing 3D objects from multiple scans taken from different viewpoints is a classical problem
Textured surfaces captured by two calibrated Kinects
The two captured RGB-D images are converted to a 3D mesh surface with texture information using the OpenNI package
Summary
Reconstructing 3D objects from multiple scans taken from different viewpoints is a classical problem. Registration involves two intertwined problems: establishing correct correspondences between points on different surfaces, and finding a suitable spatial transformation or deformation that puts these surfaces into alignment. This is a computationally expensive task; most methods iteratively optimize correspondences and transformations alternately. Texture misalignments are typically much more noticeable to the eye than geometric misalignments To overcome this problem, we present a novel color-aware registration algorithm that produces high-quality registration of textured surfaces. While we have mainly tested the algorithm on our own data, we believe it to be generally useful, as identical problems are likely to arise in other RGB-D capture systems when capturing subjects with rich color textures.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
