LimeCross: Context-Conditioned Layered Image Editing with Structural Consistency

• URL: http://arxiv.org/abs/2605.10319v1
• Date: Mon, 11 May 2026 10:18:28 GMT
• Title: LimeCross: Context-Conditioned Layered Image Editing with Structural Consistency
• Abstract summary: We propose LimeCross, a training-free context-conditioned layered image editing framework.<n>It edits user-selected RGBA layers according to text while keeping the remaining layers unchanged.<n>Experiments demonstrate that LimeCross improves layer purity and composite realism over strong editing baselines.
• Score: 7.077690782604656
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Layered image assets are widely used in real-world creative workflows, enabling non-destructive iteration and flexible re-composition. Recent advances in layered image generation and decomposition synthesize or recover layered representations, yet controllable editing of layered images remains challenging. Manual editing requires careful coordination across layers to maintain consistent illumination and contact, while AI-based pipelines collapse layers into a flattened image for editing, then decompose them again, introducing background-to-foreground leakage and unstable transparency. To address these limitations, we propose LimeCross, a training-free context-conditioned layered image editing framework that edits user-selected RGBA layers according to text while keeping the remaining layers unchanged. It leverages contextual cues from other layers using a bi-stream attention mechanism to preserve cross-layer consistency, while explicitly maintaining layer integrity to prevent the contamination of edited layers. To evaluate our approach, we introduce LayerEditBench, a benchmark of 1500 layered scenes with paired source/target prompts, along with evaluation protocols that assess both edit fidelity and alpha channel stability. Extensive experiments demonstrate that LimeCross improves layer purity and composite realism over strong editing baselines, establishing context-conditioned layered editing as a principled framework for controllable generative creation.

Related papers

• ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition [60.25038184390257]
  ReDesign is an agentic framework that grows an editable layer hierarchy by selecting and composing specialized tools across modalities.<n>To evaluate editability at scale, we introduce the Figma Edit Replay Benchmark consisting of 909 raw Figma files and 14,796 controlled edit instructions that replay edits on reconstructed outputs.
  arXiv  Detail & Related papers  (2026-07-28T10:53:33Z)
• RevealLayer: Disentangling Hidden and Visible Layers via Occlusion-Aware Image Decomposition [16.33087128655428]
  We propose RevealLayer, a diffusion-based framework that decomposes an RGB image into multiple RGBA layers.<n>To support training and evaluation, we introduce RevealLayer-100K, a high-quality multi-layer natural image constructed through a collaboration between automated algorithms and human annotation.
  arXiv  Detail & Related papers  (2026-05-12T09:09:01Z)
• Edge-Aware Image Manipulation via Diffusion Models with a Novel Structure-Preservation Loss [32.26030534230571]
  We propose a novel Structure Preservation Loss (SPL) to quantify structural differences between input and edited images.<n>Our training-free approach integrates SPL directly into the diffusion model's generative process to ensure structural fidelity.<n> Experiments confirm SPL enhances structural fidelity, delivering state-of-the-art performance in latent-diffusion-based image editing.
  arXiv  Detail & Related papers  (2026-01-23T11:06:51Z)
• Controllable Layered Image Generation for Real-World Editing [49.81321254149423]
  LASAGNA is a novel, unified framework that generates an image jointly with its composing layers.<n>We introduce LASAGNA-48K, a new dataset composed of clean backgrounds and RGBA foregrounds with physically grounded visual effects.<n>We demonstrate that LASAGNA excels in generating highly consistent and coherent results across multiple image layers simultaneously.
  arXiv  Detail & Related papers  (2026-01-21T22:29:33Z)
• Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition [73.43121650616804]
  We propose textbfQwen-Image-Layered, an end-to-end diffusion model that decomposes a single RGB image into multiple semantically disentangled RGBA layers.<n>Our method significantly surpasses existing approaches in decomposition quality and establishes a new paradigm for consistent image editing.
  arXiv  Detail & Related papers  (2025-12-17T17:12:42Z)
• OmniPSD: Layered PSD Generation with Diffusion Transformer [59.20320950128599]
  We propose OmniPSD, a unified diffusion framework built upon the Flux ecosystem.<n>It enables text-to-PSD generation and image-to-PSD decomposition through in-context learning.<n>Experiments on our new RGBA-layered dataset demonstrate that OmniPSD achieves high-fidelity generation.
  arXiv  Detail & Related papers  (2025-12-10T02:09:59Z)
• From Inpainting to Layer Decomposition: Repurposing Generative Inpainting Models for Image Layer Decomposition [16.7393689710179]
  layered representation enables independent editing of elements, offering greater flexibility for content creation.<n>We observe a strong connection between layer decomposition and in/outpainting tasks, and propose adapting a diffusion-based inpainting model for layer decomposition using lightweight finetuning.<n>To further preserve detail in the latent space, we introduce a novel multi-modal context fusion module with linear attention complexity.
  arXiv  Detail & Related papers  (2025-11-26T02:50:07Z)
• LayerD: Decomposing Raster Graphic Designs into Layers [15.294433619347082]
  LayerD is a method to decompose graphic designs into layers for re-editable creative workflow.<n>We propose a simple yet effective refinement approach taking advantage of the assumption that layers often exhibit uniform appearance.<n>In experiments, we show that LayerD successfully achieves high-quality decomposition and outperforms baselines.
  arXiv  Detail & Related papers  (2025-09-29T17:50:12Z)
• DiffDecompose: Layer-Wise Decomposition of Alpha-Composited Images via Diffusion Transformers [85.1185656296496]
  We present DiffDecompose, a diffusion Transformer-based framework that learns the posterior over possible layer decompositions conditioned on the input image.<n>The code and dataset will be available upon paper acceptance.
  arXiv  Detail & Related papers  (2025-05-24T16:08:04Z)
• Generative Image Layer Decomposition with Visual Effects [49.75021036203426]
  LayerDecomp is a generative framework for image layer decomposition.<n>It produces clean backgrounds and high-quality transparent foregrounds with faithfully preserved visual effects.<n>Our method achieves superior quality in layer decomposition, outperforming existing approaches in object removal and spatial editing tasks.
  arXiv  Detail & Related papers  (2024-11-26T20:26:49Z)
• Stable Flow: Vital Layers for Training-Free Image Editing [74.52248787189302]
  Diffusion models have revolutionized the field of content synthesis and editing.<n>Recent models have replaced the traditional UNet architecture with the Diffusion Transformer (DiT)<n>We propose an automatic method to identify "vital layers" within DiT, crucial for image formation.<n>Next, to enable real-image editing, we introduce an improved image inversion method for flow models.
  arXiv  Detail & Related papers  (2024-11-21T18:59:51Z)
• LayerDiffusion: Layered Controlled Image Editing with Diffusion Models [5.58892860792971]
  LayerDiffusion is a semantic-based layered controlled image editing method. We leverage a large-scale text-to-image model and employ a layered controlled optimization strategy. Experimental results demonstrate the effectiveness of our method in generating highly coherent images.
  arXiv  Detail & Related papers  (2023-05-30T01:26:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.