Physics-guided Shape-from-Template: Monocular Video Perception through Neural Surrogate Models
This addresses the problem of slow and noisy reconstruction for dynamic scenes in computer graphics, particularly for cloth, with incremental improvements in speed and stability.
The paper tackles 3D reconstruction of cloth from monocular video by proposing a Shape-from-Template method that uses a neural surrogate model for fast, stable, and smooth reconstructions, reducing runtime by a factor of 400-500 compared to a state-of-the-art physics-based approach.
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 cloth using a pre-trained neural surrogate model that is fast to evaluate, stable, and produces smooth reconstructions due to a regularizing physics simulation. Differentiable rendering of the simulated mesh enables pixel-wise comparisons between the reconstruction and a target video sequence that can be used for a gradient-based optimization procedure to extract not only shape information but also physical parameters such as stretching, shearing, or bending stiffness of the cloth. This allows to retain a precise, stable, and smooth reconstructed geometry while reducing the runtime by a factor of 400-500 compared to $φ$-SfT, a state-of-the-art physics-based SfT approach.