Reconstruct room and polygonal scenes using guided diffusion with PolyDiffuse
Reconstruct room and polygonal scenes using guided diffusion with PolyDiffuse
PolyDiffuse: Polygonal Shape Reconstruction via Guided Set Diffusion Models
arXiv paper abstract https://arxiv.org/abs/2306.01461
arXiv PDF paper https://arxiv.org/pdf/2306.01461.pdf
Project page https://poly-diffuse.github.io
... presents PolyDiffuse, a novel structured reconstruction algorithm that transforms visual sensor data into polygonal shapes with Diffusion Models (DM) ... formulating reconstruction as a generation process conditioned on sensor data.
... introduction of a Guided Set Diffusion Model where
1) the forward diffusion process learns guidance networks to control noise injection so that one representation of a sample remains distinct from its other permutation variants ...
2) the reverse denoising process reconstructs polygonal shapes, initialized and directed by the guidance networks, as a conditional generation process subject to the sensor data.
... evaluated ... approach for reconstructing ... floorplan as a set of polygons and HD map for autonomous cars as a set of polylines.
... demonstrate that PolyDiffuse significantly advances the current state of the art and enables broader practical applications.
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
Commentaires