Physics-guided Shape-from-Template: Monocular Video Perception through Neural Surrogate Models

arXiv:2311.12796v2 Announce Type: replace-cross
Abstract: 3D reconstruction of dynamic scenes is a long-standing problem in computer graphics and increasingly difficult the less information is available. Shape-from-Template (SfT) methods aim to reconstruct a template-based geometry from RGB images or video sequences, often leveraging just a single monocular camera without depth information, such as regular smartphone recordings. Unfortunately, existing reconstruction methods are either unphysical and noisy or slow in optimization. To solve this problem, we propose a novel SfT reconstruction algorithm for …

3d reconstruction abstract aim arxiv computer computer graphics cs.cv cs.lg dynamic geometry graphics images information perception physics sft template through type video