SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.06107 · ICCV · 2023

PATMAT: Person Aware Tuning of Mask-Aware Transformer for Face inpainting

Jianjin Xu, Chen Wu, Saman Motamed, Fernando De La Torre, Christian Häne, Jean-Charles Bazin

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

An illustration of PATMAT's identity preserving inpainting. By using reference images of Taylor Swift and Dwayne Johnson, PATMAT enables Mask-Aware Transformer to preserve the identity of the person. We also show results of recent methods such as MyStyle [25], trained with the same number of reference images as PATMAT and RePaint[22] that is not fine-tuned with any reference images.

For agents

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

get_harvested_code_for_paper("2304.06107")
get_code_for_paper("2304.06107")
have("2304.06107")

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

curl https://syntology.ai/api/ran/2304.06107.json

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

[![Syntology run record](https://syntology.ai/api/ran/2304.06107.svg)](https://syntology.ai/paper/2304.06107)

Connect an agent — have() is free.