Salvato in:
Dettagli Bibliografici
Autore principale: Liu, Rui
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2502.17093
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917935143976960
author Liu, Rui
author_facet Liu, Rui
contents Real-world image matting is essential for applications in content creation and augmented reality. However, it remains challenging due to the complex nature of scenes and the scarcity of high-quality datasets. To address these limitations, we introduce Mask2Alpha, an iterative refinement framework designed to enhance semantic comprehension, instance awareness, and fine-detail recovery in image matting. Our framework leverages self-supervised Vision Transformer features as semantic priors, strengthening contextual understanding in complex scenarios. To further improve instance differentiation, we implement a mask-guided feature selection module, enabling precise targeting of objects in multi-instance settings. Additionally, a sparse convolution-based optimization scheme allows Mask2Alpha to recover high-resolution details through progressive refinement,from low-resolution semantic passes to high-resolution sparse reconstructions. Benchmarking across various real-world datasets, Mask2Alpha consistently achieves state-of-the-art results, showcasing its effectiveness in accurate and efficient image matting.
format Preprint
id arxiv_https___arxiv_org_abs_2502_17093
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Image Matting in Real-World Scenes with Mask-Guided Iterative Refinement
Liu, Rui
Computer Vision and Pattern Recognition
Real-world image matting is essential for applications in content creation and augmented reality. However, it remains challenging due to the complex nature of scenes and the scarcity of high-quality datasets. To address these limitations, we introduce Mask2Alpha, an iterative refinement framework designed to enhance semantic comprehension, instance awareness, and fine-detail recovery in image matting. Our framework leverages self-supervised Vision Transformer features as semantic priors, strengthening contextual understanding in complex scenarios. To further improve instance differentiation, we implement a mask-guided feature selection module, enabling precise targeting of objects in multi-instance settings. Additionally, a sparse convolution-based optimization scheme allows Mask2Alpha to recover high-resolution details through progressive refinement,from low-resolution semantic passes to high-resolution sparse reconstructions. Benchmarking across various real-world datasets, Mask2Alpha consistently achieves state-of-the-art results, showcasing its effectiveness in accurate and efficient image matting.
title Enhancing Image Matting in Real-World Scenes with Mask-Guided Iterative Refinement
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.17093