SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.00432 · NeurIPS · 2024

Localize, Understand, Collaborate: Semantic-Aware Dragging via Intention Reasoner

Peipei Li, Zhaofeng He, Xing Cui, Zekun Li, Xuannan Liu, Yueying Zou

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

Source prompt: "Two horses." Target prompt: "Two horses with long necks." Source prompt: "Two horses." Target prompt: "Two horses with heads up." Source prompt: "Two horses far away." Target prompt: "Two horses close to each other." Diverse results generated by our LucidDrag. Image & User Edit LucidDrag Image & User Edit LucidDrag LucidDrag Image & User Edit Image & User Edit Figure 1: Given an input image, the user draws a mask specifying the editable region and clicks dragging points (handle points (red) and target points (blue)). Our LucidDrag considers the ill-posed nature of drag-based editing and can produce diverse results (the first row). Besides, it achieves outstanding performance in editing accuracy and image fidelity (the second row).

For agents

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

get_harvested_code_for_paper("2406.00432")
get_code_for_paper("2406.00432")
have("2406.00432")

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

curl https://syntology.ai/api/ran/2406.00432.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.00432.svg)](https://syntology.ai/paper/2406.00432)

Connect an agent — have() is free.