Aliasing Detection in Rendered Images via a Multi-Task Learning

Author:

Fan Shu-Ho1ORCID,Hsiao Kai-Wen1ORCID,Tan Kai Yi2ORCID,Yao Chih-Yuan3ORCID,Chu Hung-Kuo1ORCID

Affiliation:

1. National Tsing-Hua University, Taiwan

2. Tunghai University, Taiwan

3. National Taiwan University of Science and Technology, Taiwan

Abstract

As technology advances from simple 2D designs to intricate 3D environments, the demand for high-quality visuals in video games and interactive media necessitates robust image quality assessment (IQA) techniques. Traditional methods like PSNR and SSIM, reliant on reference images, struggle with the unique challenges of 3D rendered content, highlighting the need for specialized non-reference IQA approaches. This paper introduces a novel multi-task learning architecture that corrects and predicts aliasing artifacts simultaneously, enhancing predictive accuracy without reference images. It also incorporates temporal information to improve visual coherence and smoothness. An automated labeling pipeline developed using Unity ensures a stable and unbiased dataset for model training and evaluation. Our experiments demonstrate that this approach reliably detects aliasing across various complexities, achieving state-of-the-art performance. By addressing specific challenges in rendered image assessment and leveraging innovative learning techniques, our work advances IQA for video games and simulations, ensuring high visual quality.

Publisher

Association for Computing Machinery (ACM)

Reference25 articles.

1. AMD. 2023. FidelityFX Super Resolution 2. https://gpuopen.com/fidelityfx-superresolution-2/.

2. Pontus Andersson, Jim Nilsson, Tomas Akenine-Möller, Magnus Oskarsson, Karl Johan Åström, and Mark D. Fairchild. 2020. FLIP: A Difference Evaluator for Alternating Images. Proc. ACM Comput. Graph. Interact. Tech. 3 (2020), 15:1--15:23. https://api.semanticscholar.org/CorpusID:220643528

3. Real Image Denoising With Feature Attention

4. Kernel-predicting convolutional networks for denoising Monte Carlo renderings

5. DehazeNet: An End-to-End System for Single Image Haze Removal

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3