Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.11416 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909172759527424 |
|---|---|
| author | Cao, Zihan Wu, Xiao Deng, Liang-Jian |
| author_facet | Cao, Zihan Wu, Xiao Deng, Liang-Jian |
| contents | Recent diffusion probabilistic models (DPM) in the field of pansharpening have been gradually gaining attention and have achieved state-of-the-art (SOTA) performance. In this paper, we identify shortcomings in directly applying DPMs to the task of pansharpening as an inverse problem: 1) initiating sampling directly from Gaussian noise neglects the low-resolution multispectral image (LRMS) as a prior; 2) low sampling efficiency often necessitates a higher number of sampling steps. We first reformulate pansharpening into the stochastic differential equation (SDE) form of an inverse problem. Building upon this, we propose a Schrödinger bridge matching method that addresses both issues.
We design an efficient deep neural network architecture tailored for the proposed SB matching.
In comparison to the well-established DL-regressive-based framework and the recent DPM framework, our method demonstrates SOTA performance with fewer sampling steps. Moreover, we discuss the relationship between SB matching and other methods based on SDEs and ordinary differential equations (ODEs), as well as its connection with optimal transport.
Code will be available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_11416 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Neural Shrödinger Bridge Matching for Pansharpening Cao, Zihan Wu, Xiao Deng, Liang-Jian Computer Vision and Pattern Recognition Recent diffusion probabilistic models (DPM) in the field of pansharpening have been gradually gaining attention and have achieved state-of-the-art (SOTA) performance. In this paper, we identify shortcomings in directly applying DPMs to the task of pansharpening as an inverse problem: 1) initiating sampling directly from Gaussian noise neglects the low-resolution multispectral image (LRMS) as a prior; 2) low sampling efficiency often necessitates a higher number of sampling steps. We first reformulate pansharpening into the stochastic differential equation (SDE) form of an inverse problem. Building upon this, we propose a Schrödinger bridge matching method that addresses both issues. We design an efficient deep neural network architecture tailored for the proposed SB matching. In comparison to the well-established DL-regressive-based framework and the recent DPM framework, our method demonstrates SOTA performance with fewer sampling steps. Moreover, we discuss the relationship between SB matching and other methods based on SDEs and ordinary differential equations (ODEs), as well as its connection with optimal transport. Code will be available. |
| title | Neural Shrödinger Bridge Matching for Pansharpening |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.11416 |