SpaceEdit: Learning a Unified Editing Space for Open-Domain Image Editing
arXiv:2112.00180
Abstract
Recently, large pretrained models (e.g., BERT, StyleGAN, CLIP) have shown great knowledge transfer and generalization capability on various downstream tasks within their domains. Inspired by these efforts, in this paper we propose a unified model for open-domain image editing focusing on color and tone adjustment of open-domain images while keeping their original content and structure. Our model learns a unified editing space that is more semantic, intuitive, and easy to manipulate than the operation space (e.g., contrast, brightness, color curve) used in many existing photo editing softwares. Our model belongs to the image-to-image translation framework which consists of an image encoder and decoder, and is trained on pairs of before- and after-images to produce multimodal outputs. We show that by inverting image pairs into latent codes of the learned editing space, our model can be leveraged for various downstream editing tasks such as language-guided image editing, personalized editing, editing-style clustering, retrieval, etc. We extensively study the unique properties of the editing space in experiments and demonstrate superior performance on the aforementioned tasks.
References in corpus (7)
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Learning Transferable Visual Models From Natural Language Supervision
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Large Scale Image Completion via Co-Modulated Generative Adversarial Networks
- Controlling generative models with continuous factors of variations
- The Geometry of Deep Generative Image Models and its Applications
- Open-Edit: Open-Domain Image Manipulation with Open-Vocabulary Instructions