shitagaki-lab/see-through

Health v2 · maintenance only

Flags: no_releases young

Adoption not part of the score

3641 stars · 332 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A research framework from a SIGGRAPH 2026 paper that decomposes a single anime character illustration into up to 23 fully inpainted, semantically distinct layers with inferred drawing order, enabling 2.5D manipulation. It is a Python/PyTorch codebase with optional annotator tiers and online demos.

Use cases

• decompose an anime illustration into editable layers
• turn a static anime image into a 2.5D model
• extract hair, face, eyes, and clothing layers from one image
• generate inpainted PSD layers from anime art
• reorder and animate anime character parts from a single picture

When to choose

• you need layer separation for anime-style artwork specifically
• you want a research-grade, open-source implementation with a paper backing
• you have a CUDA or ROCm GPU for inference

When to avoid

• you need layer decomposition of photorealistic images rather than anime characters
• you want a polished end-user GUI application rather than a Python research codebase
• you have no GPU and cannot run heavy deep-learning inference locally

Facets

library · maturity active

image-processing machine-learning deep-learning computer-vision graphics computer-vision image-processing graphics machine-learning python windows layer-decomposition anime 2-5d-models image-inpainting siggraph research-code psd gpu linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="shitagaki-lab/see-through")