A Comparative Study of Perceptual Quality Metrics for Audio-driven Talking Head Videos
This work addresses a critical gap in performance evaluation for talking head generation, which is important for researchers and developers in AIGC, though it is incremental as it validates existing metrics rather than introducing new ones.
The study tackled the lack of validated evaluation metrics for audio-driven talking head videos by conducting psychophysical experiments on videos from four generative methods, finding that certain metrics better align with human opinions on visual quality, lip-audio synchronization, and head movement naturalness.
The rapid advancement of Artificial Intelligence Generated Content (AIGC) technology has propelled audio-driven talking head generation, gaining considerable research attention for practical applications. However, performance evaluation research lags behind the development of talking head generation techniques. Existing literature relies on heuristic quantitative metrics without human validation, hindering accurate progress assessment. To address this gap, we collect talking head videos generated from four generative methods and conduct controlled psychophysical experiments on visual quality, lip-audio synchronization, and head movement naturalness. Our experiments validate consistency between model predictions and human annotations, identifying metrics that align better with human opinions than widely-used measures. We believe our work will facilitate performance evaluation and model development, providing insights into AIGC in a broader context. Code and data will be made available at https://github.com/zwx8981/ADTH-QA.