arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2309.02405cs.CVcs.SDeess.AS
收藏

从野外声音生成逼真图像

Generating Realistic Images from In-the-wild Sounds

Artificial Intelligence Graduate School, UNIST(蔚山科学技术院人工智能研究生院)

Taegyeong Lee, Jeonghun Kang, Hyeonyu Kim, Taehwan Kim

AI总结:

本文提出一种从野外声音生成逼真图像的新方法,通过音频字幕、音频与句子注意力及CLIPscore优化,利用扩散模型生成,实验优于基线。

摘要:

将野外声音表示为图像是一项重要但具有挑战性的任务,原因在于声音与图像之间缺乏配对数据集,且这两种模态的特征存在显著差异。以往的研究集中于从有限类别或音乐中生成图像。本文提出了一种从野外声音生成图像的新方法。首先,我们利用音频字幕将声音转换为文本。其次,我们提出了音频注意力和句子注意力来表征声音的丰富特征并可视化声音。最后,我们提出了结合CLIPscore和AudioCLIP的直接声音优化方法,并利用基于扩散的模型生成图像。实验表明,我们的模型能够从野外声音生成高质量图像,并在野外音频数据集上的定量和定性评估中均优于基线方法。

英文摘要:

Representing wild sounds as images is an important but challenging task due to the lack of paired datasets between sound and images and the significant differences in the characteristics of these two modalities. Previous studies have focused on generating images from sound in limited categories or music. In this paper, we propose a novel approach to generate images from in-the-wild sounds. First, we convert sound into text using audio captioning. Second, we propose audio attention and sentence attention to represent the rich characteristics of sound and visualize the sound. Lastly, we propose a direct sound optimization with CLIPscore and AudioCLIP and generate images with a diffusion-based model. In experiments, it shows that our model is able to generate high quality images from wild sounds and outperforms baselines in both quantitative and qualitative evaluations on wild audio datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑