Hear-Your-Click: Interactive Object-Specific Video-to-Audio Generation

TL;DR

Hear-Your-Click introduces an interactive video-to-audio generation framework that allows users to generate sounds for specific objects in videos by clicking, utilizing object-aware features and novel data augmentation strategies.

Contribution

The paper presents a new interactive V2A method with object-level control, novel contrastive fine-tuning, and tailored augmentation strategies for improved object-specific audio generation.

Findings

Enhanced control over object-specific audio generation

Improved alignment between visual objects and generated sounds

Superior performance on new evaluation metric CAV score

Abstract

Video-to-audio (V2A) generation shows great potential in fields such as film production. Despite significant advances, current V2A methods relying on global video information struggle with complex scenes and generating audio tailored to specific objects. To address these limitations, we introduce Hear-Your-Click, an interactive V2A framework enabling users to generate sounds for specific objects by clicking on the frame. To achieve this, we propose Object-aware Contrastive Audio-Visual Fine-tuning (OCAV) with a Mask-guided Visual Encoder (MVE) to obtain object-level visual features aligned with audio. Furthermore, we tailor two data augmentation strategies, Random Video Stitching (RVS) and Mask-guided Loudness Modulation (MLM), to enhance the model's sensitivity to segmented objects. To measure audio-visual correspondence, we designed a new evaluation metric, the CAV score. Extensive experiments demonstrate that our framework offers more precise control and improves generation performance across various metrics. Project Page: https://github.com/SynapGrid/Hear-Your-Click