3D-LFM: Lifting Foundation Model

arXiv:2312.11894v2 Announce Type: replace-cross
Abstract: The lifting of 3D structure and camera from 2D landmarks is at the cornerstone of the entire discipline of computer vision. Traditional methods have been confined to specific rigid objects, such as those in Perspective-n-Point (PnP) problems, but deep learning has expanded our capability to reconstruct a wide range of object classes (e.g. C3DPO and PAUL) with resilience to noise, occlusions, and perspective distortions. All these techniques, however, have been limited by the fundamental need …

abstract arxiv capability computer computer vision cs.ai cs.cv cs.lg deep learning foundation foundation model object objects perspective pnp type vision