Get 3D shape of object by neural reconstruction enhanced with depth from multiple views with CVRecon
Get 3D shape of object by neural reconstruction enhanced with depth from multiple views with CVRecon
CVRecon: Rethinking 3D Geometric Feature Learning For Neural Reconstruction
arXiv paper abstract https://arxiv.org/abs/2304.14633
arXiv PDF paper https://arxiv.org/pdf/2304.14633.pdf
Project page https://cvrecon.ziyue.cool
Recent advances in neural reconstruction using posed image sequences have made remarkable progress.
... due to the lack of depth ... existing volumetric-based techniques simply duplicate 2D image features of the object surface along the entire camera ray.
... duplication introduces noise in empty and occluded spaces, posing challenges for producing high-quality 3D geometry.
Drawing inspiration from traditional multi-view stereo methods ... propose an end-to-end 3D neural reconstruction framework CVRecon, designed to exploit the rich geometric embedding in the cost volumes to facilitate 3D geometric feature learning.
... present Ray-contextual Compensated Cost Volume (RCCV), a novel 3D geometric feature representation that encodes view-dependent information with improved integrity and robustness.
... approach significantly improves the reconstruction quality in various metrics and recovers clear fine details of the 3D geometries ...
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