Salient Image Matting
Rahul Deora, Rishab Sharma, Dinesh Samuel Sathia Raj

TL;DR
The paper introduces Salient Image Matting, an automatic, end-to-end framework that estimates foreground opacity in images using saliency detection and a novel multi-scale architecture, reducing the need for costly trimap annotations.
Contribution
It presents a fully automatic salient image matting framework that combines saliency detection with a multi-scale fusion architecture, enabling accurate alpha matte estimation without manual trimaps.
Findings
Produces high-quality alpha mattes for diverse images.
Requires less annotated data than traditional methods.
Outperforms state-of-the-art matting techniques.
Abstract
In this paper, we propose an image matting framework called Salient Image Matting to estimate the per-pixel opacity value of the most salient foreground in an image. To deal with a large amount of semantic diversity in images, a trimap is conventionally required as it provides important guidance about object semantics to the matting process. However, creating a good trimap is often expensive and timeconsuming. The SIM framework simultaneously deals with the challenge of learning a wide range of semantics and salient object types in a fully automatic and an end to end manner. Specifically, our framework is able to produce accurate alpha mattes for a wide range of foreground objects and cases where the foreground class, such as human, appears in a very different context than the train data directly from an RGB input. This is done by employing a salient object detection model to produce a…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage Enhancement Techniques · Visual Attention and Saliency Detection · Advanced Image Fusion Techniques
