DynamicSurf: Dynamic Neural RGB-D Surface Reconstruction with an Optimizable Feature Grid
This addresses the challenging setting of monocular 3D reconstruction for deforming surfaces, offering faster optimization for applications like robotics or animation, though it is incremental in improving existing neural methods.
DynamicSurf tackles the problem of high-fidelity 3D reconstruction of non-rigid surfaces from monocular RGB-D video by using a learned feature grid, achieving a 6x speedup over MLP-based approaches with comparable accuracy to state-of-the-art methods.
We propose DynamicSurf, a model-free neural implicit surface reconstruction method for high-fidelity 3D modelling of non-rigid surfaces from monocular RGB-D video. To cope with the lack of multi-view cues in monocular sequences of deforming surfaces, one of the most challenging settings for 3D reconstruction, DynamicSurf exploits depth, surface normals, and RGB losses to improve reconstruction fidelity and optimisation time. DynamicSurf learns a neural deformation field that maps a canonical representation of the surface geometry to the current frame. We depart from current neural non-rigid surface reconstruction models by designing the canonical representation as a learned feature grid which leads to faster and more accurate surface reconstruction than competing approaches that use a single MLP. We demonstrate DynamicSurf on public datasets and show that it can optimize sequences of varying frames with $6\times$ speedup over pure MLP-based approaches while achieving comparable results to the state-of-the-art methods. Project is available at https://mirgahney.github.io//DynamicSurf.io/.