FastLLVE: Real-Time Low-Light Video Enhancement with Intensity-Aware Lookup Table

TL;DR

FastLLVE introduces a real-time low-light video enhancement method using an adaptive, intensity-aware lookup table that maintains inter-frame consistency and achieves high-quality results at over 50 FPS.

Contribution

The paper proposes FastLLVE, a novel low-light video enhancement pipeline leveraging a learnable intensity-aware LUT for real-time, high-quality, and temporally consistent video enhancement.

Findings

Achieves state-of-the-art image quality and inter-frame consistency.

Processes 1080p videos at over 50 FPS, twice as fast as CNN-based methods.

Maintains high enhancement quality with low latency and complexity.

Abstract

Low-Light Video Enhancement (LLVE) has received considerable attention in recent years. One of the critical requirements of LLVE is inter-frame brightness consistency, which is essential for maintaining the temporal coherence of the enhanced video. However, most existing single-image-based methods fail to address this issue, resulting in flickering effect that degrades the overall quality after enhancement. Moreover, 3D Convolution Neural Network (CNN)-based methods, which are designed for video to maintain inter-frame consistency, are computationally expensive, making them impractical for real-time applications. To address these issues, we propose an efficient pipeline named FastLLVE that leverages the Look-Up-Table (LUT) technique to maintain inter-frame brightness consistency effectively. Specifically, we design a learnable Intensity-Aware LUT (IA-LUT) module for adaptive enhancement, which addresses the low-dynamic problem in low-light scenarios. This enables FastLLVE to perform low-latency and low-complexity enhancement operations while maintaining high-quality results. Experimental results on benchmark datasets demonstrate that our method achieves the State-Of-The-Art (SOTA) performance in terms of both image quality and inter-frame brightness consistency. More importantly, our FastLLVE can process 1,080p videos at $\mathit{50+}$ Frames Per Second (FPS), which is $\mathit{2 \times}$ faster than SOTA CNN-based methods in inference time, making it a promising solution for real-time applications. The code is available at https://github.com/Wenhao-Li-777/FastLLVE.