PickScan: Object discovery and reconstruction from handheld interactions
V van der Brugge, M Pollefeys… - 2024 IEEE/RSJ …, 2024 - ieeexplore.ieee.org
Reconstructing compositional 3D representations of scenes, where each object is
represented with its own 3D model, is a highly desirable capability in robotics and
augmented reality. However, most existing methods rely heavily on strong appearance
priors for object discovery, therefore only working on those classes of objects on which the
method has been trained, or do not allow for object manipulation, which is necessary to scan
objects fully and to guide object discovery in challenging scenarios. We address these …
represented with its own 3D model, is a highly desirable capability in robotics and
augmented reality. However, most existing methods rely heavily on strong appearance
priors for object discovery, therefore only working on those classes of objects on which the
method has been trained, or do not allow for object manipulation, which is necessary to scan
objects fully and to guide object discovery in challenging scenarios. We address these …
PickScan: Object discovery and reconstruction from handheld interactions
V Brugge, M Pollefeys… - … (IROS 2024), Abu …, 2024 - research-collection.ethz.ch
Reconstructing compositional 3D representations of scenes, where each object is
represented with its own 3D model, is a highly desirable capability in robotics and
augmented reality. However, most existing methods rely heavily on strong appearance
priors for object discovery, therefore only working on those classes of objects on which the
method has been trained, or do not allow for object manipulation, which is necessary to scan
objects fully and to guide object discovery in challenging scenarios. We address these …
represented with its own 3D model, is a highly desirable capability in robotics and
augmented reality. However, most existing methods rely heavily on strong appearance
priors for object discovery, therefore only working on those classes of objects on which the
method has been trained, or do not allow for object manipulation, which is necessary to scan
objects fully and to guide object discovery in challenging scenarios. We address these …