Pith. sign in

REVIEW 5 cited by

Text2Layer: Layered Image Generation using Latent Diffusion Model

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2307.09781 v1 pith:UGEQSNY2 submitted 2023-07-19 cs.CV cs.AIcs.LG

Xinyang Zhang , Wentian Zhao , Xin Lu , Jeff Chien This is my paper · ORCID
classification cs.CVcs.AIcs.LG
keywords imagelayeredlayercompositingdiffusiongenerationablebenefit
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Layer compositing is one of the most popular image editing workflows among both amateurs and professionals. Motivated by the success of diffusion models, we explore layer compositing from a layered image generation perspective. Instead of generating an image, we propose to generate background, foreground, layer mask, and the composed image simultaneously. To achieve layered image generation, we train an autoencoder that is able to reconstruct layered images and train diffusion models on the latent representation. One benefit of the proposed problem is to enable better compositing workflows in addition to the high-quality image output. Another benefit is producing higher-quality layer masks compared to masks produced by a separate step of image segmentation. Experimental results show that the proposed method is able to generate high-quality layered images and initiates a benchmark for future work.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition

    cs.CV 2026-07 conditional novelty 6.0 of 10

    ReDesign turns screenshots into editable layer hierarchies by having a vision-language agent choose tools step by step and verify each split, beating layered-decomposition baselines on a new Figma edit-replay benchmark.

  2. RaDL: Relation-aware Disentangled Learning for Multi-Instance Text-to-Image Generation

    cs.CV 2025-07 conditional novelty 6.0 of 10

    RaDL adds two attention modules to a Stable Diffusion based pipeline: Attribute Enhancement for per-instance attribute fidelity and Relation Attention that uses action verbs from the prompt to model inter-instance rel...

  3. Rethinking Layered Graphic Design Generation with a Top-Down Approach

    cs.CV 2025-07 conditional novelty 6.0 of 10

    Accordion decomposes AI-generated raster designs into editable background, object, and vectorized text layers using a VLM-driven top-down planning pipeline.

  4. PrismLayers: Open Data for High-Quality Multi-Layer Transparent Image Generative Models

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A new open dataset and synthesis pipeline for high-quality multi-layer transparent images, plus a fine-tuned ART+ model that users preferred over the original ART in about 60 percent of comparisons.

  5. LumiGen: An LVLM-Enhanced Iterative Framework for Fine-Grained Text-to-Image Generation

    cs.LG 2025-08 reject novelty 4.0 of 10

    An LVLM-driven iterative text-to-image framework whose claimed performance scores are explicitly labeled fictitious, so no empirical result is established.

Pith tools