Build a Restoration Workflow for a Digital Heritage Archive
Overview
What this challenge is about.
Build a Restoration Workflow for a Digital Heritage Archive. Intermediate challenge in analysis. Analyzing real datasets and building models that drive decis...
The Brief
What you'll do, and what you'll demonstrate.
Restore 50 glass-plate scans with a reproducible workflow plus a publishable methodology note that holds up to conservator scrutiny.
This is not a data exercise. It is the work an analyst does when stakeholders need answers from messy data. That distinction matters to every hiring manager who has seen candidates describe statistical methods and none who have extracted insight from messy, real-world data.
When you finish, you will have something most graduates do not: a real-world deliverable, verified by Ewance, that you can show to a hiring manager and say "I did this. Here is the proof."
Earning criteria — what you'll demonstrate
- Combine inpainting, density correction, and denoising in a reproducible pipeline
- Reason about restoration ethics (what to edit, what to leave)
- Validate restoration quality with a domain-expert blind scoring
- Author a public methodology note that meets archival standards
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Aligned coursework coming soon.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
- Image Restoration
Apply image restoration to solve real industry problems and demonstrate production-level capability.
- Inpainting
Apply inpainting to solve real industry problems and demonstrate production-level capability.
- Tone Mapping
Apply tone mapping to solve real industry problems and demonstrate production-level capability.
- Computational Imaging
Apply computational imaging to solve real industry problems and demonstrate production-level capability.
- Process Documentation
Apply process documentation to solve real industry problems and demonstrate production-level capability.
- Reproducibility
Apply reproducibility to solve real industry problems and demonstrate production-level capability.
Careers
Career paths this challenge builds toward
Completing this challenge demonstrates skills that transfer directly to these roles:
Applied AI Scientist
Translating image-processing research into a reproducible, ethically scoped client deliverable is the day-to-day of applied AI scientists at vertical consultancies.
This challenge sharpens
- image-restoration
- process-documentation
- reproducibility
Computer Vision Engineer
Building reproducible classical restoration pipelines is the CV-engineer foundation that complements modern deep-learning work.
This challenge sharpens
- image-restoration
- inpainting
- tone-mapping
AI Safety Researcher
Pre-registering an editing policy and publishing a methodology note is precisely the kind of transparency safety researchers advocate for in generative-AI tooling.
This challenge sharpens
- process-documentation
- computational-imaging
- reproducibility