# DSM Refinement with Deep Encoder-Decoder Networks

arXiv: https://arxiv.org/abs/2012.07427 · HTML: https://mlsanity.com/paper/2012.07427/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Dec 2020.

## Built on by (most cited first, 1 of 1)

- [SridBench: Benchmark of Scientific Research Illustration Drawing of Image Generation Model](https://mlsanity.com/paper/2505.22126/) (2025)

## Abstract (arXiv)

3D city models can be generated from aerial images. However, the calculated DSMs suffer from noise, artefacts, and data holes that have to be manually cleaned up in a time-consuming process. This work presents an approach that automatically refines such DSMs. The key idea is to teach a neural network the characteristics of urban area from reference data. In order to achieve this goal, a loss function consisting of an L1 norm and a feature loss is proposed. These features are constructed using a pre-trained image classification network. To learn to update the height maps, the network architecture is set up based on the concept of deep residual learning and an encoder-decoder structure. The results show that this combination is highly effective in preserving the relevant geometric structures while removing the undesired artefacts and noise.