Get 3D object shape from sparse views with noisy poses by consistent surface in views with SC-NeuS
Get 3D object shape from sparse views with noisy poses by consistent surface in views with SC-NeuS
SC-NeuS: Consistent Neural Surface Reconstruction from Sparse and Noisy Views
arXiv paper abstract https://arxiv.org/abs/2307.05892
arXiv PDF paper https://arxiv.org/pdf/2307.05892.pdf
... neural surface reconstruction by volume rendering ... achieving impressive surface reconstruction ... but are still limited to dense and highly accurate posed views.
To overcome ... drawbacks, this paper pays special attention ... surface reconstruction from sparse views with noisy camera poses.
... exploit the multi-view constraints directly from the explicit geometry of the neural surface, which can be used as effective regularization to jointly learn the neural surface and refine the camera poses.
To build effective multi-view constraints, ... introduce a fast differentiable on-surface intersection to generate on-surface points, and propose view-consistent losses based on such differentiable points to regularize the neural surface learning.
... propose a jointly learning strategy for neural surface and camera poses, named SC-NeuS, to perform geometry-consistent surface reconstruction in an end-to-end manner.
... SC-NeuS can achieve consistently better surface reconstruction results with fine-grained details than previous state-of-the-art ... especially from sparse and noisy camera views.
Please like and share this post if you enjoyed it using the buttons at the bottom!
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
Komentáře