SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.18068 · 2024

SynArtifact: Classifying and Alleviating Artifacts in Synthetic Images via Vision-Language Model

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

In the rapidly evolving area of image synthesis, a serious challenge is the presence of complex artifacts that compromise perceptual realism of synthetic images. To alleviate artifacts and improve quality of synthetic images, we fine-tune Vision-Language Model (VLM) as artifact classifier to automatically identify and classify a wide range of artifacts and provide supervision for further optimizing generative models. Specifically, we develop a comprehensive artifact taxonomy and construct a dataset of synthetic images with artifact annotations for fine-tuning VLM, named SynArtifact-1K. The fine-tuned VLM exhibits superior ability of identifying artifacts and outperforms the baseline by 25.66%. To our knowledge, this is the first time such end-to-end artifact classification task and solution have been proposed. Finally, we leverage the output of VLM as feedback to refine the generative model for alleviating artifacts. Visualization results and user study demonstrate that the quality of images synthesized by the refined diffusion model has been obviously improved.

For agents

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

get_harvested_code_for_paper("2402.18068")
get_code_for_paper("2402.18068")
have("2402.18068")

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

curl https://syntology.ai/api/ran/2402.18068.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.18068.svg)](https://syntology.ai/paper/2402.18068)

Connect an agent — have() is free.