Learning Camera-Agnostic White-Balance Preferences

2025-07-02

AI Summary

Existing cross-camera automatic white balance (AWB) methods primarily target neutral color temperature correction, failing to ensure aesthetic style consistency across multi-camera systems. This paper introduces the first camera-agnostic aesthetic white balance mapping framework: building upon standard neutral AWB outputs, it learns a lightweight post-processing mapping—from neutral to aesthetically preferred color correction—with only ~500 parameters, requiring no modification to the existing ISP pipeline. By projecting illumination estimation into a unified, camera-agnostic feature space, the method achieves consistent aesthetic color rendering across heterogeneous sensors. Evaluated on a benchmark of 771 multi-camera smartphone images, it achieves state-of-the-art performance, with per-frame inference latency of merely 0.024 ms—imposing virtually zero computational overhead. The approach significantly enhances visual consistency in multi-camera systems deployed on resource-constrained edge devices.

Technology Category

• Computer Vision: Computational Photography, Image & Video Synthesis
• Machine Learning: Hardware-aware ML
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

The image signal processor (ISP) pipeline in modern cameras consists of several modules that transform raw sensor data into visually pleasing images in a display color space. Among these, the auto white balance (AWB) module is essential for compensating for scene illumination. However, commercial AWB systems often strive to compute aesthetic white-balance preferences rather than accurate neutral color correction. While learning-based methods have improved AWB accuracy, they typically struggle to generalize across different camera sensors -- an issue for smartphones with multiple cameras. Recent work has explored cross-camera AWB, but most methods remain focused on achieving neutral white balance. In contrast, this paper is the first to address aesthetic consistency by learning a post-illuminant-estimation mapping that transforms neutral illuminant corrections into aesthetically preferred corrections in a camera-agnostic space. Once trained, our mapping can be applied after any neutral AWB module to enable consistent and stylized color rendering across unseen cameras. Our proposed model is lightweight -- containing only $sim$500 parameters -- and runs in just 0.024 milliseconds on a typical flagship mobile CPU. Evaluated on a dataset of 771 smartphone images from three different cameras, our method achieves state-of-the-art performance while remaining fully compatible with existing cross-camera AWB techniques, introducing minimal computational and memory overhead.

Problem

• Achieving aesthetic white-balance consistency across different cameras
• Transforming neutral illuminant corrections into preferred aesthetic corrections
• Ensuring lightweight and efficient cross-camera color rendering

Innovation

• Learns aesthetic white-balance preferences post-illuminant-estimation
• Camera-agnostic mapping for consistent color rendering
• Lightweight model with minimal computational overhead