Abstract
We present a novel approach to automatically recover, from a small set of partially overlapping spherical images, an indoor structure representation in terms of a 3D floor plan registered with a set of 3D environment maps. We introduce several improvements over previous approaches based on color and spatial reasoning exploiting Manhattan world priors. In particular, we introduce a new method for geometric context extraction based on a 3D facet representation, which combines color distribution analysis of individual images with sparse multi-view clues. We also introduce an efficient method to combine the facets from different viewpoints in a single consistent model, taking into the reliability of the facet information. The resulting capture and reconstruction pipeline automatically generates 3D multi-room environments in cases where most previous approaches fail, e.g., in the presence of hidden corners and large clutter, without the need for additional dense 3D data or tools. We demonstrate the effectiveness and performance of our approach on different real-world indoor scenes. Our test data is available to allow further studies and comparisons.
Highlights
1.1 Background The consumer-oriented industry’s interest in spherical images has dramatically increased in recent years
We developed a reconstruction pipeline that, starting from a collection of spherical images and their multi-view alignment, automatically produces a structured 3D floor plan in terms of interconnected rooms bounded by walls
We have presented a novel and practical approach for recovering 3D indoor structures using low-cost 360◦ cameras
Summary
1.1 Background The consumer-oriented industry’s interest in spherical images has dramatically increased in recent years. Numerous consumer-grade 360◦ cameras have recently become available or are about to be released, allowing consumers to acquire and share panoramic images, or even to capture compelling imagery for stereo viewing in a head-mounted display [2] While such spherical images could previously be obtained by stitching conventional photographic shots, for instance with the help of special-purpose sensor fusion applications on mobile cameras and phones [3, 4], the emergence of these new 360◦ cameras is significantly reducing the effort needed to capture such images. Large and complex environments can be captured with very few single-shot 360◦ images, whose overlap can provide registration information Such sparse, but visually rich, coverage is a very interesting and simple alternative to dense shape capture, as done with scanners or dense multi-view images. Solutions based on low-cost devices play an even more important role for privacy reasons, as they allow individual users to acquire and share their own environments using consumer-level tools, without the need for physical access by other persons for the scanning process [6]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
