SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2205.08324 · 2022

Exploring the Interactive Guidance for Unified and Effective Image Matting

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recent image matting studies are developing towards proposing trimap-free or interactive methods for complete complex image matting tasks. Although avoiding the extensive labors of trimap annotation, existing methods still suffer from two limitations: (1) For the single image with multiple objects, it is essential to provide extra interaction information to help determining the matting target; (2) For transparent objects, the accurate regression of alpha matte from RGB image is much more difficult compared with the opaque ones. In this work, we propose a Unified Interactive image Matting method, named UIM, which solves the limitations and achieves satisfying matting results for any scenario. Specifically, UIM leverages multiple types of user interaction to avoid the ambiguity of multiple matting targets, and we compare the pros and cons of different annotation types in detail. To unify the matting performance for transparent and opaque objects, we decouple image matting into two stages, i.e., foreground segmentation and transparency prediction. Moreover, we design a multi-scale attentive fusion module to alleviate the vagueness in the boundary region. Experimental results demonstrate that UIM achieves state-of-the-art performance on the Composition-1K test set and a synthetic unified dataset.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2205.08324")
get_code_for_paper("2205.08324")
have("2205.08324")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2205.08324.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2205.08324.svg)](https://syntology.ai/paper/2205.08324)

Connect an agent — have() is free.