shitagaki-lab/see-through
"Single-image Layer Decomposition for Anime Characters" (SIGGRAPH 2026 Conference Paper)
Turning Flat Anime Art into Layered 2.5D Models — A SIGGRAPH 2026 research project that decomposes a single anime illustration into up to 23 fully inpainted, semantically labeled layers (hair, face, eyes, clothing, accessories) with inferred drawing order. Useful for artists and researchers wanting editable PSD-like outputs or 2.5D rigs from flat art, with live Hugging Face and ModelScope demos.
Metrics
Relative growth (7d)+6%Growth over the last 7 days relative to size
Acceleration+110%Change in growth pace from the week before
Attention64The three metrics scaled to 0–100 and combined
Retention can be computed 30 days after a repository first trends (it isn't shown until then). See About for how each metric is defined.
Star growth and Trending appearances (last 30 days)
First listed+106★/dayDaily
Sep 30, 2026Oct 29, 2026
Bands mark days on the trending list (darker = higher rank)
Daily trending ranks as a table (1 days)
| Date | Daily |
|---|---|
| Oct 29, 2026 | python #9 +74 |
Created Mar 31, 2026 · First on trending Oct 29, 2026