TGTM: TinyML-based Global Tone Mapping for HDR Sensors
This addresses the challenge of real-time image processing for vehicle cameras in high-contrast lighting conditions, though it appears incremental as it builds on existing tone mapping methods.
The paper tackles the problem of inefficient tone mapping for HDR sensors in ADAS by proposing TGTM, a lightweight neural network method that operates at 9,000 FLOPS per image and achieves up to 5.85 dB higher PSNR than state-of-the-art methods.
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.