Structure from Motion: Theoretical Foundations of a Novel Approach Using Custom Built Invariants
Pierre-Louis Bazin, Mireille Boutin
Abstract
We rephrase the problem of 3D reconstruction from images in terms of intersections of projections of orbits of custom built Lie groups actions. We then use an algorithmic method based on moving frames "a la Fels-Olver" to obtain a fundamental set of invariants of these groups actions. The invariants are used to define a set of equations to be solved by the points of the 3D object, providing a new technique for recovering 3D structure from motion.
Create a lesson
Related papers
FlowSGS: Improving Flow Matching Priors for Inverse Imaging with Stochastic Interpolants
Tianao Li, Xinhui Qian, Emma Alexander
Should This Case Be Adapted? Prediction Fragmentation Controls Test-Time Adaptation
Lili Wang, Jing Li, Xiaowen Sun et al.
FunArt: Decoding Functional Structure and Articulation from Generative 3D Latents
Dennis Rotondi, Abdelrhman Werby, Kai O. Arras
Earth Surface Immune System for Rapid Monitoring of Unknown Anomalies
Jingtao Li, Qian Zhu, Xinyu Wang et al.
PROVIA: Procedure State Tracking for Online Mistake Detection in Egocentric Videos
Di Wen, Kailun Yang, Jimmy Weissert et al.
Refinement Is Inherently Editable: Training-Free Prompt-to-Prompt Image Editing with Generative Refinement Network
Yulong Chen, Ziqian Zhang, Haoyu Zhang et al.