DeepAI AI Chat
Log In Sign Up

SpaceEdit: Learning a Unified Editing Space for Open-Domain Image Editing

by   Jing Shi, et al.

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.


page 1

page 14

page 15

page 16

page 17

page 18

page 19

page 20


Variational Bayesian Framework for Advanced Image Generation with Domain-Related Variables

Deep generative models (DGMs) and their conditional counterparts provide...

Style Transformer for Image Inversion and Editing

Existing GAN inversion methods fail to provide latent codes for reliable...

VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance

Generating and editing images from open domain text prompts is a challen...

Topologically-Guided Color Image Enhancement

Enhancement is an important step in post-processing digital images for p...

StyleGAN of All Trades: Image Manipulation with Only Pretrained StyleGAN

Recently, StyleGAN has enabled various image manipulation and editing ta...

A Benchmark and Baseline for Language-Driven Image Editing

Language-driven image editing can significantly save the laborious image...

Distilling Style from Image Pairs for Global Forward and Inverse Tone Mapping

Many image enhancement or editing operations, such as forward and invers...