Get 3D shape using per-pixel intensity renderings rather than estimated normals with NPLMV-PS
Get 3D shape using per-pixel intensity renderings rather than estimated normals with NPLMV-PS
NPLMV-PS: Neural Point-Light Multi-View Photometric Stereo
arXiv paper abstract https://arxiv.org/abs/2405.12057
arXiv PDF paper https://arxiv.org/pdf/2405.12057
… present a novel multi-view photometric stereo (PS) method … leveraging neural shape representations and learnt renderers.
… differs from … multi-view PS methods such as PS-NeRF or SuperNormal … explicity leverage per-pixel intensity renderings rather than relying mainly on estimated normals.
… model point light attenuation and explicitly raytrace cast shadows in order to best approximate each points incoming radiance.
This is used as input to a fully neural material renderer that uses minimal prior assumptions and it is jointly optimised with the surface.
Finally, estimated normal and segmentation maps can also incorporated in order to maximise the surface accuracy.
… outperform the classical … DiLiGenT-MV and achieves average 0.2mm Chamfer distance for objects imaged at approx 1.5m distance away with approximate 400x400 resolution …
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
