Get 3D object shape from sparse views without camera poses by aggregating 2D image feature with LEAP
Get 3D object shape from sparse views without camera poses by aggregating 2D image feature with LEAP
LEAP: Liberate Sparse-view 3D Modeling from Camera Poses
arXiv paper abstract https://arxiv.org/abs/2310.01410
arXiv PDF paper https://arxiv.org/pdf/2310.01410.pdf
Project page https://hwjiang1510.github.io/LEAP
... for multi-view 3D modeling ... Existing approaches predominantly assume access to accurate camera poses.
... present LEAP, a novel pose-free approach ... discards pose-based operations and learns geometric knowledge from data.
LEAP is equipped with a neural volume, which is shared across scenes and is parameterized to encode geometry and texture priors.
For each incoming scene, ... update the neural volume by aggregating 2D image features in a feature-similarity-driven manner.
The updated neural volume is decoded into the radiance field, enabling novel view synthesis from any viewpoint.
... show that LEAP significantly outperforms prior methods when they employ predicted poses from state-of-the-art pose estimators ...
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
Comments