# Deep Learning based Optical Image Super-Resolution via Generative Diffusion Models for Layerwise in-situ LPBF Monitoring

arXiv: https://arxiv.org/abs/2409.13171 · HTML: https://mlsanity.com/paper/2409.13171/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 19 of its 57 references that are in the map.
- First posted on arXiv 20 Sep 2024.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 19 of 19)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models](https://mlsanity.com/paper/2104.14951/) (2021)
- [Implicit Diffusion Models for Continuous Super-Resolution](https://mlsanity.com/paper/2303.16491/) (2023)
- [Deep Learning for Single Image Super-Resolution: A Brief Review](https://mlsanity.com/paper/1808.03344/) (2018)
- [Spectral Regularization for Combating Mode Collapse in GANs](https://mlsanity.com/paper/1908.10999/) (2019)
- [ESRGAN+ : Further Improving Enhanced Super-Resolution Generative Adversarial Network](https://mlsanity.com/paper/2001.08073/) (2020)
- [Pores for thought: The use of generative adversarial networks for the stochastic reconstruction of 3D multi-phase electrode microstructures with periodic boundaries](https://mlsanity.com/paper/2003.11632/) (2020)
- [Maximum Entropy Models from Phase Harmonic Covariances](https://mlsanity.com/paper/1911.10017/) (2019)
- [Inexpensive High Fidelity Melt Pool Models in Additive Manufacturing Using Generative Deep Diffusion](https://mlsanity.com/paper/2311.16168/) (2023)
- [Deep-Learned Generators of Porosity Distributions Produced During Metal Additive Manufacturing](https://mlsanity.com/paper/2205.05794/) (2022)
- [ThermoPore: Predicting Part Porosity Based on Thermal Images Using Deep Learning](https://mlsanity.com/paper/2404.16882/) (2024)

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

- [Coupled Diffusion-Encoder Models for Reconstruction of Flow Fields](https://mlsanity.com/paper/2601.07946/) (2026)

## Abstract (arXiv)

The stochastic formation of defects during Laser Powder Bed Fusion (L-PBF) negatively impacts its adoption for high-precision use cases. Optical monitoring techniques can be used to identify defects based on layer-wise imaging, but these methods are difficult to scale to high resolutions due to cost and memory constraints. Therefore, we implement generative deep learning models to link low-cost, low-resolution images of the build plate to detailed high-resolution optical images of the build plate, enabling cost-efficient process monitoring. To do so, a conditional latent probabilistic diffusion model is trained to produce realistic high-resolution images of the build plate from low-resolution webcam images, recovering the distribution of small-scale features and surface roughness. We first evaluate the performance of the model by analyzing the reconstruction quality of the generated images using peak-signal-to-noise-ratio (PSNR), structural similarity index measure (SSIM) and wavelet covariance metrics that describe the preservation of high-frequency information. Additionally, we design a framework based upon the Segment Anything foundation model to recreate the 3D morphology of the printed part and analyze the surface roughness of the reconstructed samples. Finally, we explore the zero-shot generalization capabilities of the implemented framework to other part geometries by creating synthetic low-resolution data.