TaoMate-FVSR:Audio-Guided Facial Video Restoration

Researchers introduced TaoMate-FVSR, an audio-guided facial video restoration method that uses spoken audio to guide super-resolution of small, poorly resolved face regions in AI-generated videos. The work addresses a gap the researchers identify: visual super-resolution can sharpen facial regions without resolving whether recovered lips and teeth agree with the spoken audio.

AI-generated videos often depict people within detailed scenes while leaving their small facial regions poorly resolved. Visual super-resolution can sharpen these regions without resolving whether the recovered lips and teeth agree with the spoken audio. We present an audio-guided facial video resto