Learning by Planning: Language-Guided Global Image Editing

06/24/2021
by   Jing Shi, et al.
0

Recently, language-guided global image editing draws increasing attention with growing application potentials. However, previous GAN-based methods are not only confined to domain-specific, low-resolution data but also lacking in interpretability. To overcome the collective difficulties, we develop a text-to-operation model to map the vague editing language request into a series of editing operations, e.g., change contrast, brightness, and saturation. Each operation is interpretable and differentiable. Furthermore, the only supervision in the task is the target image, which is insufficient for a stable training of sequential decisions. Hence, we propose a novel operation planning algorithm to generate possible editing sequences from the target image as pseudo ground truth. Comparison experiments on the newly collected MA5k-Req dataset and GIER dataset show the advantages of our methods. Code is available at https://jshi31.github.io/T2ONet.

READ FULL TEXT

page 7

page 8

page 12

page 13

page 14

page 15

page 16

page 17

research
10/05/2020

A Benchmark and Baseline for Language-Driven Image Editing

Language-driven image editing can significantly save the laborious image...
research
09/19/2023

Forgedit: Text Guided Image Editing via Learning and Forgetting

Text guided image editing on real images given only the image and the ta...
research
10/21/2021

Each Attribute Matters: Contrastive Attention for Sentence-based Image Editing

Sentence-based Image Editing (SIE) aims to deploy natural language to ed...
research
06/02/2022

DE-Net: Dynamic Text-guided Image Editing Adversarial Networks

Text-guided image editing models have shown remarkable results. However,...
research
07/26/2017

Pigmento: Pigment-Based Image Analysis and Editing

The colorful appearance of a physical painting is determined by the dist...
research
09/22/2022

CCR: Facial Image Editing with Continuity, Consistency and Reversibility

Three problems exist in sequential facial image editing: incontinuous ed...
research
08/04/2021

Combining Attention with Flow for Person Image Synthesis

Pose-guided person image synthesis aims to synthesize person images by t...

Please sign up or login with your details

Forgot password? Click here to reset