AVC-Reward: Event-Centric Audio-Video Consistency Evaluation
[Widzenie komputerowe] Autorzy: Yuruo Wu, Kaihang Pan, Kai Shen i 6 więcej
As joint audio-video generation models become more capable, they can generate audio-visual scenes exhibiting three forms of complexity: multi-event composition, multi-layer audio mixture, and asymmetric cross-modal relations. However, current evaluations largely reuse metrics from earlier simple and unidirectional tasks. They typically evaluate an audio-video clip as a whole and rely on simple predefined relations, making them unsuitable for these increasingly complex scenes. We propose an event-centric evaluation framework that disentangles audio and visual events at the event level, analyzes each event independently, cross-validates relations across modalities, and aggregates the judgments into a coarse-to-fine, three-level consistency metric. The metric assesses global narrative harmony, event-level temporal synchronization, and fine-grained attribute alignment, providing a general f…
- Kategoria arxiv
- cs.CV
- Kategoria
- Widzenie komputerowe