Corridor Cast EP#239 | Tech Talk - Coding, Building a Greenscreen Tool, Guassian Splats & More
Jan 23, 2026
A lively tech deep dive into building an AI tool for automatic green screen keying and the data, backbones, and refiner models behind it. A tour of Gaussian splats and neural rendering alternatives, their rapid rise, and creative uses in film and VR. Chat about LLM coding assistants, installation headaches for research tools, and plans to open-source a production-ready workflow.
AI Snips
Chapters
Transcript
Episode notes
Chroma Key As A Concept-Based Problem
- Niko reframed chroma keying as a "concept key" that predicts per-pixel foreground/background and unmixes background color from semi-transparent pixels.
- This approach combines a high-resolution backbone with a refiner model to restore fine edge detail like hair.
Iterate Rapidly With Guided Training
- Train the model on high-quality, varied green-screen data and iterate while checking outputs frequently to tweak gamma and comp equations.
- Use automated tools (like Antigravity) to speed coding cycles but remain the director of the model's behavior.
Combine High-Res Backbone With Edge Refiner
- Use a higher-resolution backbone (e.g., HIRA) for concept prediction and a secondary refiner model to recover full-resolution edges.
- Upsample concept predictions and then restore sub-pixel detail with a dedicated mini-model for hair and fine edges.