Get 3D scene from sparse annotations using diffusion model with DADP
Get 3D scene from sparse annotations using diffusion model with DADP
Diffusion-Augmented Depth Prediction with Sparse Annotations
arXiv paper abstract https://arxiv.org/abs/2308.02283
arXiv PDF paper https://arxiv.org/pdf/2308.02283.pdf
Depth estimation aims to predict dense depth maps.
In autonomous driving scenes, sparsity of annotations makes the task challenging.
... propose a supervised framework termed Diffusion-Augmented Depth Prediction (DADP).
... leverage the structural characteristics of diffusion model to enforce depth structures of depth models in a plug-and-play manner.
An object-guided integrality loss is also proposed to further enhance regional structure integrality by fetching objective information.
... achieve significant improvements in depth structures and robustness ...
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