TGTM: TinyML-based Global Tone Mapping for HDR Sensors

TL;DR

This paper introduces TGTM, a lightweight TinyML neural network for efficient global tone mapping of HDR images, significantly improving image quality while reducing computational load for vehicle ADAS systems.

Contribution

The paper presents a novel TinyML-based global tone mapping method that operates with only 9,000 FLOPS per image, enabling real-time HDR processing in resource-constrained environments.

Findings

TGTM outperforms state-of-the-art methods by up to 5.85 dB PSNR.

TGTM requires orders of magnitude less computation.

The method is adaptable to classical tone mapping techniques.

Abstract

Advanced driver assistance systems (ADAS) relying on multiple cameras are increasingly prevalent in vehicle technology. Yet, conventional imaging sensors struggle to capture clear images in conditions with intense illumination contrast, such as tunnel exits, due to their limited dynamic range. Introducing high dynamic range (HDR) sensors addresses this issue. However, the process of converting HDR content to a displayable range via tone mapping often leads to inefficient computations, when performed directly on pixel data. In this paper, we focus on HDR image tone mapping using a lightweight neural network applied on image histogram data. Our proposed TinyML-based global tone mapping method, termed as TGTM, operates at 9,000 FLOPS per RGB image of any resolution. Additionally, TGTM offers a generic approach that can be incorporated to any classical tone mapping method. Experimental results demonstrate that TGTM outperforms state-of-the-art methods on real HDR camera images by up to 5.85 dB higher PSNR with orders of magnitude less computations.