CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable, and Controllable Text-Guided Face Manipulation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhou, Chenliang, Zhong, Fangcheng, Oztireli, Cengiz
Natura: Preprint
Pubblicazione: 2022
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909764111302656
author Zhou, Chenliang
Zhong, Fangcheng
Oztireli, Cengiz
author_facet Zhou, Chenliang
Zhong, Fangcheng
Oztireli, Cengiz
contents Recently introduced Contrastive Language-Image Pre-Training (CLIP) bridges images and text by embedding them into a joint latent space. This opens the door to ample literature that aims to manipulate an input image by providing a textual explanation. However, due to the discrepancy between image and text embeddings in the joint space, using text embeddings as the optimization target often introduces undesired artifacts in the resulting images. Disentanglement, interpretability, and controllability are also hard to guarantee for manipulation. To alleviate these problems, we propose to define corpus subspaces spanned by relevant prompts to capture specific image characteristics. We introduce CLIP Projection-Augmentation Embedding (PAE) as an optimization target to improve the performance of text-guided image manipulation. Our method is a simple and general paradigm that can be easily computed and adapted, and smoothly incorporated into any CLIP-based image manipulation algorithm. To demonstrate the effectiveness of our method, we conduct several theoretical and empirical studies. As a case study, we utilize the method for text-guided semantic face editing. We quantitatively and qualitatively demonstrate that PAE facilitates a more disentangled, interpretable, and controllable image manipulation with state-of-the-art quality and accuracy. Project page: https://chenliang-zhou.github.io/CLIP-PAE/.
format Preprint
id arxiv_https___arxiv_org_abs_2210_03919
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable, and Controllable Text-Guided Face Manipulation
Zhou, Chenliang
Zhong, Fangcheng
Oztireli, Cengiz
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Recently introduced Contrastive Language-Image Pre-Training (CLIP) bridges images and text by embedding them into a joint latent space. This opens the door to ample literature that aims to manipulate an input image by providing a textual explanation. However, due to the discrepancy between image and text embeddings in the joint space, using text embeddings as the optimization target often introduces undesired artifacts in the resulting images. Disentanglement, interpretability, and controllability are also hard to guarantee for manipulation. To alleviate these problems, we propose to define corpus subspaces spanned by relevant prompts to capture specific image characteristics. We introduce CLIP Projection-Augmentation Embedding (PAE) as an optimization target to improve the performance of text-guided image manipulation. Our method is a simple and general paradigm that can be easily computed and adapted, and smoothly incorporated into any CLIP-based image manipulation algorithm. To demonstrate the effectiveness of our method, we conduct several theoretical and empirical studies. As a case study, we utilize the method for text-guided semantic face editing. We quantitatively and qualitatively demonstrate that PAE facilitates a more disentangled, interpretable, and controllable image manipulation with state-of-the-art quality and accuracy. Project page: https://chenliang-zhou.github.io/CLIP-PAE/.
title CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable, and Controllable Text-Guided Face Manipulation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2210.03919