Skip to Main content Skip to Navigation
Journal articles

Manifold surface reconstruction of an environment from sparse Structure-from-Motion data

Abstract : The majority of methods for the automatic surface reconstruction of an environment from an image sequence have two steps: Structure-from-Motion and dense stereo. From the computational standpoint, it would be interesting to avoid dense stereo and to generate a surface directly from the sparse cloud of 3D points and their visibility information provided by Structure-from-Motion. The previous attempts to solve this problem are currently very limited: the surface is non-manifold or has zero genus, the experiments are done on small scenes or objects using a few dozens of images. Our solution does not have these limitations. Furthermore, we experiment with hand-held or helmet-held catadioptric cameras moving in a city and generate 3D models such that the camera trajectory can be longer than one kilometer.
Document type :
Journal articles
Complete list of metadatas

Cited literature [44 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01635450
Contributor : Maxime Lhuillier <>
Submitted on : Wednesday, June 3, 2020 - 6:02:44 PM
Last modification on : Friday, June 5, 2020 - 4:28:05 AM

Identifiers

Citation

Maxime Lhuillier, Shuda Yu. Manifold surface reconstruction of an environment from sparse Structure-from-Motion data. Computer Vision and Image Understanding, Elsevier, 2013, 117 (11), pp.1628 - 1644. ⟨10.1016/j.cviu.2013.08.002⟩. ⟨hal-01635450⟩

Share

Metrics

Record views

8

Files downloads

32