Reconstruct 3D objects using multi-view features and signed ray distance functions with VolRecon
Reconstruct 3D objects using multi-view features and signed ray distance functions with VolRecon
VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction
arXiv paper abstract https://arxiv.org/abs/2212.08067
arXiv PDF paper https://arxiv.org/pdf/2212.08067.pdf
Project page https://fangjinhuawang.github.io/VolRecon
With the success of neural volume rendering in novel view synthesis, neural implicit reconstruction with volume rendering has become popular.
However, most methods optimize per-scene functions and are unable to generalize to novel scenes.
… introduce VolRecon, a generalizable implicit reconstruction method with Signed Ray Distance Function (SRDF).
To reconstruct with fine details and little noise, … combine projection features, aggregated from multi-view features with a view transformer, and volume features interpolated from a coarse global feature volume.
A ray transformer computes SRDF values of all the samples along a ray to estimate the surface location, which are used for volume rendering of color and depth.
… method outperforms SparseNeuS by about 30% in sparse view reconstruction and achieves comparable quality as MVSNet in full view reconstruction …
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
