Sound-Guided Semantic Image Manipulation

by   Seung-Hyun Lee, et al.

The recent success of the generative model shows that leveraging the multi-modal embedding space can manipulate an image using text information. However, manipulating an image with other sources rather than text, such as sound, is not easy due to the dynamic characteristics of the sources. Especially, sound can convey vivid emotions and dynamic expressions of the real world. Here, we propose a framework that directly encodes sound into the multi-modal (image-text) embedding space and manipulates an image from the space. Our audio encoder is trained to produce a latent representation from an audio input, which is forced to be aligned with image and text representations in the multi-modal embedding space. We use a direct latent optimization method based on aligned embeddings for sound-guided image manipulation. We also show that our method can mix text and audio modalities, which enrich the variety of the image modification. We verify the effectiveness of our sound-guided image manipulation quantitatively and qualitatively. We also show that our method can mix different modalities, i.e., text and audio, which enrich the variety of the image modification. The experiments on zero-shot audio classification and semantic-level image classification show that our proposed model outperforms other text and sound-guided state-of-the-art methods.


page 1

page 6

page 7

page 8


Robust Sound-Guided Image Manipulation

Recent successes suggest that an image can be manipulated by a text prom...

Ceci n'est pas une pomme: Adversarial Illusions in Multi-Modal Embeddings

Multi-modal encoders map images, sounds, texts, videos, etc. into a sing...

Sound-Guided Semantic Video Generation

The recent success in StyleGAN demonstrates that pre-trained StyleGAN la...

Align, Adapt and Inject: Sound-guided Unified Image Generation

Text-guided image generation has witnessed unprecedented progress due to...

Robot Synesthesia: A Sound and Emotion Guided AI Painter

If a picture paints a thousand words, sound may voice a million. While r...

LISA: Localized Image Stylization with Audio via Implicit Neural Representation

We present a novel framework, Localized Image Stylization with Audio (LI...

Embed Everything: A Method for Efficiently Co-Embedding Multi-Modal Spaces

Any general artificial intelligence system must be able to interpret, op...

Please sign up or login with your details

Forgot password? Click here to reset