RevealLayer decomposes natural images into multiple RGBA layers using diffusion models with region-aware attention, occlusion-guided adaptation, and a composite loss, outperforming prior methods on a new benchmark dataset.
Transparent image layer diffusion using latent trans- parency
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 8verdicts
UNVERDICTED 8roles
background 1polarities
background 1representative citing papers
Forking Garden generates branching dungeon graphs from user-provided storylines by creating a pool of independent nodes and assembling them via arc-guided constraint algorithms that enforce multimodal alignment of gameplay elements.
LASAGNA produces layered images with integrated visual effects in a single pass, enabling drift-free edits via alpha compositing while releasing a 48K dataset and a 242-sample benchmark.
PAI-Studio reformulates cinematic background replacement as in-context conditional generation inside a Diffusion Transformer with bidirectional attention, trained on a new 30K film-sourced dataset, and reports better motion consistency and relighting than prior open-source and commercial systems.
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.
CatalogStitch provides dimension-aware mask computation and occlusion-aware hybrid restoration to automate corrections in generative object compositing for catalog images.
BLK-Assist is a three-part framework (Conceptor for sketches, Stencil for transparent assets, Upscale for high-res outputs) that fine-tunes public diffusion models on one artist's proprietary corpus for style-faithful generative co-creation.
citing papers explorer
-
RevealLayer: Disentangling Hidden and Visible Layers via Occlusion-Aware Image Decomposition
RevealLayer decomposes natural images into multiple RGBA layers using diffusion models with region-aware attention, occlusion-guided adaptation, and a composite loss, outperforming prior methods on a new benchmark dataset.
-
The Garden of Forking Paths: Narrative Arc-Conditioned Gameplay Planning
Forking Garden generates branching dungeon graphs from user-provided storylines by creating a pool of independent nodes and assembling them via arc-guided constraint algorithms that enforce multimodal alignment of gameplay elements.
-
A Unified and Controllable Framework for Layered Image Generation with Visual Effects
LASAGNA produces layered images with integrated visual effects in a single pass, enabling drift-free edits via alpha compositing while releasing a 48K dataset and a 242-sample benchmark.
-
PAI-Studio: Cinematic Video Background Replacement with Camera-Aware Motion
PAI-Studio reformulates cinematic background replacement as in-context conditional generation inside a Diffusion Transformer with bidirectional attention, trained on a new 30K film-sourced dataset, and reports better motion consistency and relighting than prior open-source and commercial systems.
-
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.
-
CatalogStitch: Dimension-Aware and Occlusion-Preserving Object Compositing for Catalog Image Generation
CatalogStitch provides dimension-aware mask computation and occlusion-aware hybrid restoration to automate corrections in generative object compositing for catalog images.
-
BLK-Assist: A Methodological Framework for Artist-Led Co-Creation with Generative AI Models
BLK-Assist is a three-part framework (Conceptor for sketches, Stencil for transparent assets, Upscale for high-res outputs) that fine-tunes public diffusion models on one artist's proprietary corpus for style-faithful generative co-creation.