Stable-Layers applies Flow-GRPO with LoRA and a two-stage VLM scoring pipeline to improve layer decomposition without paired supervision, yielding stronger separation and lower reconstruction error on Crello.
From inpainting to layer decomposition: Repurposing generative inpainting models for image layer decomposition
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 4years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
Presents LiWi-100k dataset generated via agent-driven decomposition and a model achieving SoTA on RGB L1 and Alpha IoU for natural image layering.
LimeCross enables text-guided editing of individual layers in composite images by conditioning on cross-layer context via bi-stream attention while preserving layer integrity and introducing the LayerEditBench benchmark.
MIRAGE introduces a benchmark for multi-instance image editing and a training-free framework that uses vision-language parsing and parallel regional denoising to achieve precise edits without altering backgrounds.
citing papers explorer
-
Stable-Layers: Fine-Tuning Image Layer Decomposition Models with VLM-Scored Reinforcement Learning
Stable-Layers applies Flow-GRPO with LoRA and a two-stage VLM scoring pipeline to improve layer decomposition without paired supervision, yielding stronger separation and lower reconstruction error on Crello.
-
LiWi: Layering in the Wild
Presents LiWi-100k dataset generated via agent-driven decomposition and a model achieving SoTA on RGB L1 and Alpha IoU for natural image layering.
-
LimeCross: Context-Conditioned Layered Image Editing with Structural Consistency
LimeCross enables text-guided editing of individual layers in composite images by conditioning on cross-layer context via bi-stream attention while preserving layer integrity and introducing the LayerEditBench benchmark.
-
MIRAGE: Benchmarking and Aligning Multi-Instance Image Editing
MIRAGE introduces a benchmark for multi-instance image editing and a training-free framework that uses vision-language parsing and parallel regional denoising to achieve precise edits without altering backgrounds.