Image Demoir'eing Using Dual Camera Fusion on Mobile Phones

2025-06-10

AI Summary

To address severe moiré artifacts degrading image quality in smartphone-captured screen photos, this paper proposes a dual-camera collaborative moiré removal method that leverages complementary information from ultra-wide and wide-angle views—marking the first work to enable joint modeling of smartphone dual cameras for moiré suppression. Key contributions include: (1) constructing the first large-scale real-world dual-camera moiré dataset (9,000 image pairs); (2) designing a lightweight ultra-wide encoder and a feature-based two-stage fast alignment mechanism to improve cross-view registration accuracy; and (3) introducing a dual-stream fusion network for end-to-end moiré removal optimization. Experiments demonstrate that our method significantly outperforms existing state-of-the-art approaches on the proposed dataset, while maintaining low model complexity and fast inference speed—enabling real-time deployment on mobile devices. The code and dataset are publicly released.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Mixture of Experts (MoE)
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

When shooting electronic screens, moir'e patterns usually appear in captured images, which seriously affects the image quality. Existing image demoir'eing methods face great challenges in removing large and heavy moir'e. To address the issue, we propose to utilize Dual Camera fusion for Image Demoir'eing (DCID), ie, using the ultra-wide-angle (UW) image to assist the moir'e removal of wide-angle (W) image. This is inspired by two motivations: (1) the two lenses are commonly equipped with modern smartphones, (2) the UW image generally can provide normal colors and textures when moir'e exists in the W image mainly due to their different focal lengths. In particular, we propose an efficient DCID method, where a lightweight UW image encoder is integrated into an existing demoir'eing network and a fast two-stage image alignment manner is present. Moreover, we construct a large-scale real-world dataset with diverse mobile phones and monitors, containing about 9,000 samples. Experiments on the dataset show our method performs better than state-of-the-art methods. Code and dataset are available at https://github.com/Mrduckk/DCID.

Problem

• Remove moiré patterns from mobile phone images
• Utilize dual camera fusion for demoiréing
• Improve image quality with ultra-wide-angle assistance

Innovation

• Dual Camera fusion for moiré removal
• Lightweight UW image encoder integration
• Fast two-stage image alignment