# Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment Source: [Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment]() Collection index: [llms.txt]() Data updated: 2025-10-28T13:56:58.296Z Authors: Kim Sung-Bin, Arda Senocak, Hyunwoo Ha, Andrew Owens, Tae-Hyun Oh Published: 2023-03-30T16:01:50.000Z ## Abstract How does audio describe the world around us? In this paper, we propose a method for generating an image of a scene from sound. Our method addresses the challenges of dealing with the large gaps that often exist between sight and sound. We design a model that works by scheduling the learning procedure of each model component to associate audio-visual modalities despite their information gaps. The key idea is to enrich the audio features with visual information by learning to align audio to visual latent space. We translate the input audio to visual features, then use a pre-trained generator to produce an image. To further improve the quality of our generated images, we use sound source localization to select the audio-visual pairs that have strong cross-modal correlations. We obtain substantially better results on the VEGAS and VGGSound datasets than prior approaches. We also show that we can control our model's predictions by applying simple manipulations to the input waveform, or to the latent space. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Soundscape-to-image generation on SonicUrban 237K](): Soundscape-to-image generation; SonicUrban 237K; FID: 49.681. - [Soundscape-to-image generation on SoundingSVI 169K](): Soundscape-to-image generation; SoundingSVI 169K; FID: 78.137. ## Original sources and implementation [Original paper]() [PDF]()