Nonrigid Structure-From-Motion via Differential Geometry With Recoverable Conformal Scale

Nonrigid structure-from-motion (NRSfM), a promising technique for addressing the mapping challenges in monocular visual deformable simultaneous localization and mapping, has attracted growing attention. We introduce a novel method, called Con-NRSfM, for NRSfM under conformal deformations, encompassi...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on robotics Ročník 41; s. 6229 - 6249
Hlavní autoři: Chen, Yongbo, Zhang, Yanhao, Parashar, Shaifali, Zhao, Liang, Huang, Shoudong
Médium: Journal Article
Jazyk:angličtina
Vydáno: IEEE 2025
Témata:
Accuracy
Cameras
Conformal deformations
deformable simultaneous localization and mapping (SLAM)
Deformation
encoder and decoder network
Image reconstruction
nonrigid structure-from-motion (NRSfM)
Optimization
parallel separable iterative optimization
Robots
Shape
Simultaneous localization and mapping
Surface reconstruction
Three-dimensional displays
ISSN:1552-3098, 1941-0468
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Nonrigid structure-from-motion (NRSfM), a promising technique for addressing the mapping challenges in monocular visual deformable simultaneous localization and mapping, has attracted growing attention. We introduce a novel method, called Con-NRSfM, for NRSfM under conformal deformations, encompassing isometric deformations as a subset. Our approach performs point-wise reconstruction using 2-D selected image warps optimized through a graph-based framework. Unlike existing methods that rely on strict assumptions, such as locally planar surfaces or locally linear deformations, and fail to recover the conformal scale, our method eliminates these constraints and accurately computes the local conformal scale. In addition, our framework decouples constraints on depth and conformal scale, which are inseparable in other approaches, enabling more precise depth estimation. To address the sensitivity of the formulated problem, we employ a parallel separable iterative optimization strategy. Furthermore, a self-supervised learning framework, utilizing an encoder-decoder network, is incorporated to generate dense 3-D point clouds with texture. Simulation and experimental results using both synthetic and real datasets demonstrate that our method surpasses existing approaches in terms of reconstruction accuracy and robustness.
ISSN:1552-3098
1941-0468
DOI:10.1109/TRO.2025.3621422