# CreatiParser: Generative Image Parsing of Raster Graphic Designs into Editable Layers

arXiv: https://arxiv.org/abs/2604.19632 · HTML: https://mlsanity.com/paper/2604.19632/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 68 references that are in the map.
- First posted on arXiv 21 Apr 2026.

## Builds on (most cited first, 30 of 36)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Aligning Large Multimodal Models with Factually Augmented RLHF](https://mlsanity.com/paper/2309.14525/) (2023)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback](https://mlsanity.com/paper/2312.00849/) (2023)
- [Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer](https://mlsanity.com/paper/2511.22699/) (2025)
- [VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2504.06958/) (2025)
- [Seedream 4.0: Toward Next-generation Multimodal Image Generation](https://mlsanity.com/paper/2509.20427/) (2025)
- [OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning](https://mlsanity.com/paper/2505.08617/) (2025)
- [RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness](https://mlsanity.com/paper/2405.17220/) (2024)
- [Perception-R1: Pioneering Perception Policy with Reinforcement Learning](https://mlsanity.com/paper/2504.07954/) (2025)
- [Transparent Image Layer Diffusion using Latent Transparency](https://mlsanity.com/paper/2402.17113/) (2024)
- [CanvasVAE: Learning to Generate Vector Graphic Documents](https://mlsanity.com/paper/2108.01249/) (2021)
- [DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment](https://mlsanity.com/paper/2304.04514/) (2023)
- [MM-RLHF: The Next Step Forward in Multimodal LLM Alignment](https://mlsanity.com/paper/2502.10391/) (2025)
- [CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation](https://mlsanity.com/paper/2412.03859/) (2024)
- [Ground-R1: Incentivizing Grounded Visual Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2505.20272/) (2025)
- [MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation](https://mlsanity.com/paper/2404.02790/) (2024)
- [CreatiDesign: A Unified Multi-Conditional Diffusion Transformer for Creative Graphic Design](https://mlsanity.com/paper/2505.19114/) (2025)
- [Generative Image Layer Decomposition with Visual Effects](https://mlsanity.com/paper/2411.17864/) (2024)
- [Instance-wise Occlusion and Depth Orders in Natural Scenes](https://mlsanity.com/paper/2111.14562/) (2021)

## Built on by (most cited first, 9 of 9)

- [Audio-Visual Exchange-Aware Token Pruning for Efficient Audio-Visual Captioning](https://mlsanity.com/paper/2606.10533/) (2026)
- [EmoStyle: Affective Conditioning of Style-Specialist Experts for Emotional Image Generation](https://mlsanity.com/paper/2607.10165/) (2026)
- [Geometry-aware Gaussian Prior and Axial Attention for Cervical Cytology Image Classification](https://mlsanity.com/paper/2607.10278/) (2026)
- [HTT-Net: Hierarchical Text-guided Transition Modeling for Surgical Video Phase Recognition](https://mlsanity.com/paper/2607.16787/) (2026)
- [Rationale-Guided Knowledge Distillation for Cross-Lingual Stance Detection](https://mlsanity.com/paper/2607.18693/) (2026)
- [GDB-Reward: From Evaluation Metrics to Training Rewards for Graphic Design](https://mlsanity.com/paper/2609.02813/) (2026)
- [VectorHarness: Recovering Editable, Relation-Preserving Structure from Scientific Graphics](https://mlsanity.com/paper/2609.13294/) (2026)
- [DSPO: Diversity-aware Subjective Policy Optimization for Robust Emotional Reasoning](https://mlsanity.com/paper/2609.36775/) (2026)
- [Decoding Affective Nuances: Enhancing MLLMs via Hierarchical Emotion Reasoning and Contrastive Discriminative Pruning](https://mlsanity.com/paper/2609.36782/) (2026)

## Abstract (arXiv)

Graphic design images consist of multiple editable layers, such as text, background, and decorative elements, while most generative models produce rasterized outputs without explicit layer structures, limiting downstream editing. Existing graphic design parsing methods typically rely on multi-stage pipelines combining layout prediction, matting, and inpainting, which suffer from error accumulation and limited controllability. We propose a hybrid generative framework for raster-to-layer graphic design parsing that decomposes a design image into editable text, background, and sticker layers. Text regions are parsed using a vision-language model into a text rendering protocol, enabling faithful reconstruction and flexible re-editing, while background and sticker layers are generated using a multi-branch diffusion architecture with RGBA support. We further introduce ParserReward and integrate it with Group Relative Policy Optimization to align generation quality with human design preferences. Extensive experiments on two challenging datasets, i.e., the Parser-40K and Crello datasets, demonstrate superior performance over existing methods, eg., achieving an overall average improvement of 23.7% across all metrics.