SuperPrimitive: Scene reconstruction at a primitive level
File(s)
OA Location
Author(s)
Mazur, Kirill
Bae, Gwangbin
Davison, Andrew J
Type
Conference Paper
Abstract
Joint camera pose and dense geometry estimation from a set of images or a monocular video remains a challenging problem due to its computational complexity and inherent visual ambiguities. Most dense incremental reconstruction systems operate directly on image pixels and solve for their 3D positions using multi-view geometry cues. Such pixellevel approaches suffer from ambiguities or violations of multi-view consistency (e.g. caused by textureless or specular surfaces). We address this issue with a new image representation which we call a SuperPrimitive. SuperPrimitives are obtained by splitting images into semantically correlated local regions and enhancing them with estimated surface normal directions, both of which are predicted by state-of-the-art single image neural networks. This provides a local geometry estimate per SuperPrimitive, while their relative positions are adjusted based on multi-view observations. We demonstrate the versatility of our new representation by addressing three 3D reconstruction tasks: depth completion, few-view structure from motion, and monocular dense visual odometry. Project page: https://makezur.github.io/SuperPrimitive/
Date Issued
2024-09-16
Date Acceptance
2024-06-01
Citation
2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp.4979-4989
ISBN
979-8-3503-5301-3
ISSN
1063-6919
Publisher
IEEE Computer Soc
Start Page
4979
End Page
4989
Journal / Book Title
2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Copyright Statement
© 2024 IEEE. This CVPR Workshop paper is the Open Access version, provided by the Computer Vision Foundation. Except for this watermark, it is identical to the accepted version; the final published version of the proceedings is available on IEEE Xplore.
Sponsor
Engineering & Physical Science Research Council (EPSRC)
Grant Number
EP/S036636/1
Source
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Subjects
Computer Science
Computer Science, Artificial Intelligence
Computer Science, Interdisciplinary Applications
Computer Science, Theory & Methods
Science & Technology
Technology
Publication Status
Published
Start Date
2024-06-16
Finish Date
2024-06-22
Coverage Spatial
WA, Seattle