Overview
What this challenge is about.
Build a Python avatar pipeline from a single selfie, measure fairness by demographic strata, and earn your verifiable certificate.
The scenario
NorthRoom is a 220-person San Francisco business-to-business software-as-a-service company whose virtual-meeting product renders each participant as a real-time riggable digital-human head, and its existing runtime expects heads in a fixed mesh topology and skinning format.
The Brief
What you'll do, and what you'll demonstrate.
Rebuild a single-selfie-to-riggable-avatar pipeline that runs under 90 seconds per image and delivers quality that is honestly measured and not degraded across demographic groups.
Earning criteria — what you'll demonstrate
- Fit a parametric face-shape model to landmarks and refine it with a photometric loss to reconstruct a head from one image
- Assemble a multi-stage 3D-from-image pipeline that outputs a riggable mesh conforming to a fixed runtime topology and skinning format
- Design and run a stratified evaluation that surfaces, rather than averages away, per-demographic quality gaps
- Reason about and report latency, quality, and fairness trade-offs as an engineering judgment, not just a metric dump
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.
- Digital Humans
Apply digital humans to solve real industry problems and demonstrate production-level capability.
- Geometry Processing
Apply geometry processing to solve real industry problems and demonstrate production-level capability.
- 3d Rendering
Apply 3d rendering to solve real industry problems and demonstrate production-level capability.
- Shape Modeling
Apply shape modeling to solve real industry problems and demonstrate production-level capability.
- Python
Write clean, efficient Python for data processing, automation, and backend services.
- Fairness Evaluation
Apply fairness evaluation 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:
3D Computer Vision Engineer
Reconstructing a head from a single image by fitting a parametric shape model under a photometric loss is the daily work of monocular 3D reconstruction; this challenge has you build and validate that exact loop end to end.
This challenge sharpens
- digital-humans
- geometry-processing
- shape-modeling
Avatar Graphics Engineer
Producing riggable heads that plug into a real-time runtime's fixed topology, texture, and skinning format mirrors avatar-platform engineering, where output must be both lifelike and pipeline-compatible under a tight latency budget.
This challenge sharpens
- 3d-rendering
- digital-humans
- python
Responsible AI Engineer
Designing a stratified evaluation that surfaces demographic quality gaps and turning it into a launch recommendation is core responsible-AI practice for any model that processes images of people.
This challenge sharpens
- fairness-evaluation
- python
- digital-humans