SEDiff: Structure Extraction for Domain Adaptive Depth Estimation via Denoising Diffusion Models
Abstract
In monocular depth estimation, it is challenging to acquire a large amount of depth-annotated training data, which leads to a reliance on synthetic datasets. However, the inherent discrepancies between the synthetic environment and the real-world result in a domain shift and sub-optimal performance. In this paper, we introduce SEDiff which firstly leverages a diffusion-based generative model to extract essential structural information for accurate depth estimation. SEDiff wipes out the domain-specific components in the synthetic data and enables structural-consistent style transfer to mitigate the performance degradation due to the domain gap. Extensive experiments demonstrate the superiority of SEDiff over state-of-the-art methods in various scenarios for domain-adaptive depth estimation.
Cite
Text
Shim and Kim. "SEDiff: Structure Extraction for Domain Adaptive Depth Estimation via Denoising Diffusion Models." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-72655-2_3Markdown
[Shim and Kim. "SEDiff: Structure Extraction for Domain Adaptive Depth Estimation via Denoising Diffusion Models." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/shim2024eccv-sediff/) doi:10.1007/978-3-031-72655-2_3BibTeX
@inproceedings{shim2024eccv-sediff,
title = {{SEDiff: Structure Extraction for Domain Adaptive Depth Estimation via Denoising Diffusion Models}},
author = {Shim, Dongseok and Kim, Hyoun Jin},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2024},
doi = {10.1007/978-3-031-72655-2_3},
url = {https://mlanthology.org/eccv/2024/shim2024eccv-sediff/}
}