mlsanityData to 7 Oct 2026

Road Redesign Technique Achieving Enhanced Road Safety by Inpainting with a Diffusion Model

arXiv 2302.07440 ↗First posted 15 Feb 2023cs.CV eess.IVcited by 1

Not on the map. Why?

Abstract (arXiv)

Road infrastructure can affect the occurrence of road accidents. Therefore, identifying roadway features with high accident probability is crucial. Here, we introduce image inpainting that can assist authorities in achieving safe roadway design with minimal intervention in the current roadway structure. Image inpainting is based on inpainting safe roadway elements in a roadway image, replacing accident-prone (AP) features by using a diffusion model. After object-level segmentation, the AP features identified by the properties of accident hotspots are masked by a human operator and safe roadway elements are inpainted. With only an average time of 2 min for image inpainting, the likelihood of an image being classified as an accident hotspot drops by an average of 11.85%. In addition, safe urban spaces can be designed considering human factors of commuters such as gaze saliency. Considering this, we introduce saliency enhancement that suggests chrominance alteration for a safe road view.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 15 of its 48 references that are in the map. First posted on arXiv 15 Feb 2023.

Builds on

15 of 48 references.

References · 15

  1. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  2. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  3. 2022Diffusion Models in Vision: A Surveycited by 1,008
  4. 2021Reviving Iterative Training with Mask Guidance for Interactive Segmentationcited by 162
  5. 2017Deep Extreme Cut: From Extreme Points to Object Segmentationcited by 127
  6. 2020Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learningcited by 91
  7. 2020Inter-Region Affinity Distillation for Road Marking Segmentationcited by 58
  8. 2021DRIVE: Deep Reinforced Accident Anticipation with Visual Explanationcited by 46
  9. 2021Deep Saliency Prior for Reducing Visual Distractioncited by 17
  10. 2020Look here! A parametric learning based approach to redirect visual attentioncited by 12
  11. 2020FaceLift: A transparent deep learning framework to beautify urban scenescited by 5
  12. 2020Identifying safe intersection design through unsupervised feature extraction from satellite imagerycited by 4
3 more
  1. 2022Sensing accident-prone features in urban scenes for proactive driving and accident preventioncited by 4
  2. 2021Explainable, automated urban interventions to improve pedestrian and vehicle safetycited by 3
  3. 2022Adaptive Traffic Signal Control for Developing Countries Using Fused Parameters Derived from Crowd-Source Datacited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Generative AI in the Construction Industry: Opportunities & Challengescited by 8

Similar, not cited

Close in wording, no citation either way

  1. 2024Lane Graph Extraction from Aerial Imagery via Lane Segmentation Refinement with Diffusion Models
  2. 2026Structured-Prior-Guided Diffusion Inpainting with Physical Consistency for Traffic Sign Augmentation
  3. 2025EQ-TAA: Equivariant Traffic Accident Anticipation via Diffusion-Based Accident Video Synthesis
  4. 2026AtteConDA: Attention-Based Conflict Suppression in Multi-Condition Diffusion Models and Synthetic Data Augmentation
  5. 2024Cityscape-Adverse: Benchmarking Robustness of Semantic Segmentation with Realistic Scene Modifications via Diffusion-Based Image Editing
  6. 2025InpDiffusion: Image Inpainting Localization via Conditional Diffusion Models
  7. 2024Paint by Inpaint: Learning to Add Image Objects by Removing Them First
  8. 2025From Street Views to Urban Science: Discovering Road Safety Factors with Multimodal Large Language Models