FIRM: Flexible Interactive Reflection reMoval
Xiao Chen, Xudong Jiang, Yunkang Tao, Zhen Lei, Qing Li, Chenyang Lei,, Zhaoxiang Zhang

TL;DR
FIRM introduces a flexible, interactive reflection removal framework that accepts various guidance forms, significantly reducing user effort while achieving state-of-the-art results in separating reflection layers from images.
Contribution
The paper proposes a novel unified guidance conversion module and a contrastive mask-guided network with a cross-attention mechanism, enabling flexible, efficient, and accurate reflection removal with minimal user input.
Findings
Requires only 10% of the guidance time compared to previous methods
Achieves state-of-the-art reflection removal performance on real-world datasets
Supports multiple guidance modalities such as points, boxes, strokes, and text
Abstract
Removing reflection from a single image is challenging due to the absence of general reflection priors. Although existing methods incorporate extensive user guidance for satisfactory performance, they often lack the flexibility to adapt user guidance in different modalities, and dense user interactions further limit their practicality. To alleviate these problems, this paper presents FIRM, a novel framework for Flexible Interactive image Reflection reMoval with various forms of guidance, where users can provide sparse visual guidance (e.g., points, boxes, or strokes) or text descriptions for better reflection removal. Firstly, we design a novel user guidance conversion module (UGC) to transform different forms of guidance into unified contrastive masks. The contrastive masks provide explicit cues for identifying reflection and transmission layers in blended images. Secondly, we devise 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.
Code & Models
Videos
Taxonomy
TopicsAugmented Reality Applications · Cloud Computing and Remote Desktop Technologies · Teleoperation and Haptic Systems
MethodsALIGN
