SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.04428 · CVPR · 2022

ManiTrans: Entity-Level Text-Guided Image Manipulation via Token-wise Semantic Alignment and Generation

Jianan Wang, Zhenguo Li, Chunjing Xu, Hang Xu, Guansong Lu, Yanwei Fu

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

bird1: This bird has a black head and a yellow belly. bird2: A bird is orange and black in colour, with a blue crown and black eye rings. bird1: This bird has a black head, black wings and a white belly. bird2: A red bird has a yellow head and a yellow belly with a red crown. Figure 1. Results of manipulating multiple entities according to different texts with ManiGAN [26], Lightweight-GAN [28] and our ManiTrans. Our ManiTrans can manipulate different entities accordingly, while two baseline methods fail.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2204.04428")
get_code_for_paper("2204.04428")
have("2204.04428")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2204.04428.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2204.04428.svg)](https://syntology.ai/paper/2204.04428)

Connect an agent — have() is free.