# Workflow-Aware Structured Layer Decomposition for Illustration Production

arXiv: https://arxiv.org/abs/2603.14925 · HTML: https://mlsanity.com/paper/2603.14925/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 43 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Builds on (most cited first, 26 of 26)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [Self-Supervised Scene De-occlusion](https://mlsanity.com/paper/2004.02788/) (2020)
- [Learning to generate line drawings that convey geometry and semantics](https://mlsanity.com/paper/2203.12691/) (2022)
- [ToonCrafter: Generative Cartoon Interpolation](https://mlsanity.com/paper/2405.17933/) (2024)
- [Intrinsic Image Decomposition via Ordinal Shading](https://mlsanity.com/paper/2311.12792/) (2023)
- [Colorful Diffuse Intrinsic Image Decomposition in the Wild](https://mlsanity.com/paper/2409.13690/) (2024)
- [PhysAnimator: Physics-Guided Generative Cartoon Animation](https://mlsanity.com/paper/2501.16550/) (2025)
- [ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation](https://mlsanity.com/paper/2502.18364/) (2025)
- [Generative Image Layer Decomposition with Visual Effects](https://mlsanity.com/paper/2411.17864/) (2024)
- [Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition](https://mlsanity.com/paper/2512.15603/) (2025)
- [LayerDiff: Exploring Text-guided Multi-layered Composable Image Synthesis via Layer-Collaborative Diffusion Model](https://mlsanity.com/paper/2403.11929/) (2024)
- [AniDoc: Animation Creation Made Easier](https://mlsanity.com/paper/2412.14173/) (2024)
- [LayerD: Decomposing Raster Graphic Designs into Layers](https://mlsanity.com/paper/2509.25134/) (2025)
- [MangaNinja: Line Art Colorization with Precise Reference Following](https://mlsanity.com/paper/2501.08332/) (2025)
- [DreamLayer: Simultaneous Multi-Layer Generation via Diffusion Mode](https://mlsanity.com/paper/2503.12838/) (2025)
- [Fast Soft Color Segmentation](https://mlsanity.com/paper/2004.08096/) (2020)
- [OmniPSD: Layered PSD Generation with Diffusion Transformer](https://mlsanity.com/paper/2512.09247/) (2025)
- [LayerAnimate: Layer-level Control for Animation](https://mlsanity.com/paper/2501.08295/) (2025)
- [Controllable Layer Decomposition for Reversible Multi-Layer Image Generation](https://mlsanity.com/paper/2511.16249/) (2025)
- [LayerPeeler: Autoregressive Peeling for Layer-wise Image Vectorization](https://mlsanity.com/paper/2505.23740/) (2025)
- [Semi-supervised reference-based sketch extraction using a contrastive learning framework](https://mlsanity.com/paper/2407.14026/) (2024)
- [See-through: Single-image Layer Decomposition for Anime Characters](https://mlsanity.com/paper/2602.03749/) (2026)
- [Decomposing Digital Paintings into Layers via RGB-space Geometry](https://mlsanity.com/paper/1509.03335/) (2015)

## Built on by (most cited first, 1 of 1)

- [Stable-Layers: Fine-Tuning Image Layer Decomposition Models with VLM-Scored Reinforcement Learning](https://mlsanity.com/paper/2605.30257/) (2026)

## Abstract (arXiv)

Recent generative image editing methods adopt layered representations to mitigate the entangled nature of raster images and improve controllability, typically relying on object-based segmentation. However, such strategies may fail to capture the structural and stylized properties of human-created images, such as anime illustrations. To solve this issue, we propose a workflow-aware structured layer decomposition framework tailored to the illustration production of anime artwork. Inspired by the creation pipeline of anime production, our method decomposes the illustration into semantically meaningful production layers, including line art, flat color, shadow, and highlight. To decouple all these layers, we introduce lightweight layer semantic embeddings to provide specific task guidance for each layer. Furthermore, a set of layer-wise losses is incorporated to supervise the training process of individual layers. To overcome the lack of ground-truth layered data, we construct a high-quality illustration dataset that simulated the standard anime production workflow. Experiments demonstrate that the accurate and visually coherent layer decompositions were achieved by using our method. We believe that the resulting layered representation further enables downstream tasks such as recoloring and embedding texture, supporting content creation, and illustration editing. Code is available at: https://github.com/zty0304/Anime-layer-decomposition