SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.01619 · ICCV · 2021

Deep Edge-Aware Interactive Colorization against Color-Bleeding Effects

Kaist, Jeonghoon Park, Jaegul Choo, Eungyeup Kim, Sanghyeon Lee, Somi Choi, Choonghyun Seo, Naver Webtoon

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

Figure 1: Qualitative results of edge enhancement by using our proposed method. These images are collected from https: //unsplash.com. The first and the fourth columns show samples containing color-bleeding artifacts. Yellow boxes represent color-bleeding regions. The second and the fifth columns have edge-enhanced samples by our proposed method. The scribbles utilized for edge enhancement are shown in the third and the sixth columns. Please see our project webpage for the demo video of our method.

For agents

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

get_harvested_code_for_paper("2107.01619")
get_code_for_paper("2107.01619")
have("2107.01619")

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

curl https://syntology.ai/api/ran/2107.01619.json

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

[![Syntology run record](https://syntology.ai/api/ran/2107.01619.svg)](https://syntology.ai/paper/2107.01619)

Connect an agent — have() is free.