Get 3D object shape using SDF and generalized multi-scale volume representation with GenS
Get 3D object shape using SDF and generalized multi-scale volume representation with GenS
GenS: Generalizable Neural Surface Reconstruction from Multi-View Images
arXiv paper abstract https://arxiv.org/abs/2406.02495
arXiv PDF paper https://arxiv.org/pdf/2406.02495
GitHub https://github.com/prstrive/GenS
… signed distance function (SDF) and differentiable volume rendering … powerful … for surface reconstruction from multi-view images without 3D supervision. However … impeded by … long-time per-scene optimizations and cannot generalize to new scenes.
… present GenS, an end-to-end generalizable neural surface reconstruction model. Unlike coordinate-based methods that train a separate network for each scene, … construct a generalized multi-scale volume to directly encode all scenes.
… introduce a multi-scale feature-metric consistency to impose the multi-view consistency in a more discriminative multi-scale feature space, which is robust to the failures of the photometric consistency.
And the learnable feature can be self-enhanced to continuously improve the matching accuracy and mitigate aggregation ambiguity.
… design a view contrast loss to force the model to be robust to those regions covered by few viewpoints through distilling the geometric prior from dense input to sparse input.
… model can generalize well to new scenes and outperform existing state-of-the-art methods even those employing ground-truth depth supervision …
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
