# A Sinkhorn Regularized Adversarial Network for Image Guided DEM Super-resolution using Frequency Selective Hybrid Graph Transformer

arXiv: https://arxiv.org/abs/2409.14198 · HTML: https://mlsanity.com/paper/2409.14198/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 46 references that are in the map.
- First posted on arXiv 21 Sep 2024.

## Builds on (most cited first, 23 of 23)

- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [Learning Generative Models with Sinkhorn Divergences](https://mlsanity.com/paper/1706.00292/) (2017)
- [Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs](https://mlsanity.com/paper/1704.02901/) (2017)
- [Single Image Super-Resolution via a Holistic Attention Network](https://mlsanity.com/paper/2008.08767/) (2020)
- [Stochastic Optimization for Large-scale Optimal Transport](https://mlsanity.com/paper/1605.08527/) (2016)
- [Accurate Image Restoration with Attention Retractable Transformer](https://mlsanity.com/paper/2210.01427/) (2022)
- [Towards Fast and Accurate Real-World Depth Super-Resolution: Benchmark Dataset and Baseline](https://mlsanity.com/paper/2104.06174/) (2021)
- [Deformable Kernel Networks for Joint Image Filtering](https://mlsanity.com/paper/1910.08373/) (2019)
- [A Fully Progressive Approach to Single-Image Super-Resolution](https://mlsanity.com/paper/1804.02900/) (2018)
- [Guided Depth Super-Resolution by Deep Anisotropic Diffusion](https://mlsanity.com/paper/2211.11592/) (2022)
- [SPA-GAN: Spatial Attention GAN for Image-to-Image Translation](https://mlsanity.com/paper/1908.06616/) (2019)
- [Polarized Self-Attention: Towards High-quality Pixel-wise Regression](https://mlsanity.com/paper/2107.00782/) (2021)
- [Graph Convolutional Network for Recommendation with Low-pass Collaborative Filters](https://mlsanity.com/paper/2006.15516/) (2020)
- [D-SRGAN: DEM Super-Resolution with Generative Adversarial Networks](https://mlsanity.com/paper/2004.04788/) (2020)
- [Facial Expression Restoration Based on Improved Graph Convolutional Networks](https://mlsanity.com/paper/1910.10344/) (2019)
- [DEM Super-Resolution with EfficientNetV2](https://mlsanity.com/paper/2109.09661/) (2021)
- [S2A: Wasserstein GAN with Spatio-Spectral Laplacian Attention for Multi-Spectral Band Synthesis](https://mlsanity.com/paper/2004.03867/) (2020)
- [On the Existence of Optimal Transport Gradient for Learning Generative Models](https://mlsanity.com/paper/2102.05542/) (2021)
- [Understanding the Role of Adversarial Regularization in Supervised Learning](https://mlsanity.com/paper/2010.00522/) (2020)

## Abstract (arXiv)

Digital Elevation Model (DEM) is an essential aspect in the remote sensing (RS) domain to analyze various applications related to surface elevations. Here, we address the generation of high-resolution (HR) DEMs using HR multi-spectral (MX) satellite imagery as a guide by introducing a novel hybrid transformer model consisting of Densely connected Multi-Residual Block (DMRB) and multi-headed Frequency Selective Graph Attention (M-FSGA). To promptly regulate this process, we utilize the notion of discriminator spatial maps as the conditional attention to the MX guide. Further, we present a novel adversarial objective related to optimizing Sinkhorn distance with classical GAN. In this regard, we provide both theoretical and empirical substantiation of better performance in terms of vanishing gradient issues and numerical convergence. Based on our experiments on 4 different DEM datasets, we demonstrate both qualitative and quantitative comparisons with available baseline methods and show that the performance of our proposed model is superior to others with sharper details and minimal errors.