Hi-Light: A Path to high-fidelity, high-resolution video relighting with a Novel Evaluation Paradigm

TL;DR

Hi-Light is a training-free framework for high-fidelity, high-resolution video relighting that introduces novel techniques for stability, detail preservation, and a new evaluation metric, significantly advancing the quality and consistency of relit videos.

Contribution

The paper presents Hi-Light, a novel, training-free video relighting framework with innovative modules for stability and detail preservation, and introduces the Light Stability Score for evaluation.

Findings

Outperforms state-of-the-art methods in qualitative assessments

Achieves higher lighting stability and detail preservation

Produces more consistent and visually appealing relit videos

Abstract

Video relighting offers immense creative potential and commercial value but is hindered by challenges, including the absence of an adequate evaluation metric, severe light flickering, and the degradation of fine-grained details during editing. To overcome these challenges, we introduce Hi-Light, a novel, training-free framework for high-fidelity, high-resolution, robust video relighting. Our approach introduces three technical innovations: lightness prior anchored guided relighting diffusion that stabilises intermediate relit video, a Hybrid Motion-Adaptive Lighting Smoothing Filter that leverages optical flow to ensure temporal stability without introducing motion blur, and a LAB-based Detail Fusion module that preserves high-frequency detail information from the original video. Furthermore, to address the critical gap in evaluation, we propose the Light Stability Score, the first quantitative metric designed to specifically measure lighting consistency. Extensive experiments demonstrate that Hi-Light significantly outperforms state-of-the-art methods in both qualitative and quantitative comparisons, producing stable, highly detailed relit videos.