RevealLayer: Disentangling Hidden and Visible Layers via Occlusion-Aware Image Decomposition
For computer vision researchers, this work addresses the challenging problem of layer decomposition in complex natural images, but the improvement is incremental over existing diffusion-based approaches.
RevealLayer proposes a diffusion-based framework for decomposing natural images into multiple RGBA layers, achieving precise layer separation and occlusion completion. It outperforms existing methods on the introduced RevealLayer-100K dataset and RevealLayerBench benchmark.
Recent diffusion-based approaches have made substantial progress in image layer decomposition. However, accurately decomposing complex natural images remains challenging due to difficulties in occlusion completion, robust layer disentanglement, and precise foreground boundaries. Moreover, the scarcity of high-quality multi-layer natural image datasets limits advancement. To address these challenges, we propose RevealLayer, a diffusion-based framework that decomposes an RGB image into multiple RGBA layers, enabling precise layer separation and reliable recovery of occluded content in natural images. RevealLayer incorporates three key components: (1) a Region-Aware Attention module to disentangle hidden and visible layers; (2) an Occlusion-Guided Adapter to leverage contextual information to enhance overlapping regions; and (3) a composite loss to enforce sharp alpha boundaries and suppress residual artifacts. 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, and further establish RevealLayerBench for benchmarking layer decomposition in general natural scenes. Extensive experiments demonstrate that RevealLayer consistently outperforms existing approaches in layer decomposition.