Skip to content

[TCSVT2024] MonoDiffusion: Self-Supervised Monocular Depth Estimation Using Diffusion Model

License

Notifications You must be signed in to change notification settings

ShuweiShao/MonoDiffusion

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 

Repository files navigation

MonoDiffusion: Self-Supervised Monocular Depth Estimation Using Diffusion Model

Shuwei Shao1  Zhongcai Pei1Weihai Chen1  Dingchi Sun1Peter C. Y. Chen2Zhengguo Li3
1Beihang University, 2National University of Singapore, 3A*STAR

Arxiv 2023

Abstract

We introduce a novel self-supervised depth estimation framework, dubbed MonoDiffusion, by formulating it as an iterative denoising process. Because the depth ground-truth is unavailable in the training phase, we develop a pseudo ground-truth diffusion process to assist the diffusion in MonoDiffusion. The pseudo ground-truth diffusion gradually adds noise to the depth map generated by a pre-trained teacher model. Moreover, the teacher model allows applying a distillation loss to guide the denoised depth. Further, we develop a masked visual condition mechanism to enhance the denoising ability of model. Extensive experiments are conducted on the KITTI and Make3D datasets and the proposed MonoDiffusion outperforms prior state-of-the-art competitors.
The source code is comming!

About

[TCSVT2024] MonoDiffusion: Self-Supervised Monocular Depth Estimation Using Diffusion Model

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published