# InfraDiffusion: zero-shot depth map restoration with diffusion models and prompted segmentation from sparse infrastructure point clouds

arXiv: https://arxiv.org/abs/2509.03324 · HTML: https://mlsanity.com/paper/2509.03324/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 21 of its 65 references that are in the map.
- First posted on arXiv 3 Sep 2025.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 21 of 21)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [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)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model](https://mlsanity.com/paper/2212.00490/) (2022)
- [YOLOv11: An Overview of the Key Architectural Enhancements](https://mlsanity.com/paper/2410.17725/) (2024)
- [SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud](https://mlsanity.com/paper/1809.08495/) (2018)
- [Unsupervised Degradation Representation Learning for Blind Super-Resolution](https://mlsanity.com/paper/2104.00416/) (2021)
- [LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving](https://mlsanity.com/paper/1903.08701/) (2019)
- [Frequency Separation for Real-World Super-Resolution](https://mlsanity.com/paper/1911.07850/) (2019)
- [FlowIE: Efficient Image Enhancement via Rectified Flow](https://mlsanity.com/paper/2406.00508/) (2024)
- [ExposureDiffusion: Learning to Expose for Low-light Image Enhancement](https://mlsanity.com/paper/2307.07710/) (2023)
- [Learning to Segment 3D Point Clouds in 2D Image Space](https://mlsanity.com/paper/2003.05593/) (2020)
- [Learning Prior Feature and Attention Enhanced Image Inpainting](https://mlsanity.com/paper/2208.01837/) (2022)
- [LaserSAM: Zero-Shot Change Detection Using Visual Segmentation of Spinning LiDAR](https://mlsanity.com/paper/2402.10321/) (2024)
- [RoofDiffusion: Constructing Roofs from Severely Corrupted Point Data via Diffusion](https://mlsanity.com/paper/2404.09290/) (2024)

## Abstract (arXiv)

Point clouds are widely used for infrastructure monitoring by providing geometric information, where segmentation is required for downstream tasks such as defect detection. Existing research has automated semantic segmentation of structural components, while brick-level segmentation (identifying defects such as spalling and mortar loss) has been primarily conducted from RGB images. However, acquiring high-resolution images is impractical in low-light environments like masonry tunnels. Point clouds, though robust to dim lighting, are typically unstructured, sparse, and noisy, limiting fine-grained segmentation. We present InfraDiffusion, a zero-shot framework that projects masonry point clouds into depth maps using virtual cameras and restores them by adapting the Denoising Diffusion Null-space Model (DDNM). Without task-specific training, InfraDiffusion enhances visual clarity and geometric consistency of depth maps. Experiments on masonry bridge and tunnel point cloud datasets show significant improvements in brick-level segmentation using the Segment Anything Model (SAM), underscoring its potential for automated inspection of masonry assets. Our code and data is available at https://github.com/Jingyixiong/InfraDiffusion-official-implement.