Scholarlink

In this paper, we address the recognition of motion illusions in static images. To this end, we collect a new dataset containing images both with and without motion illusions. We then benchmark state-of-the-art deep learning models to determine the presence of illusions in the images. Additionally, we assess the role of color in the recognition process. The experimental results show that deep learning models are effective in identifying motion illusions, with superior performance on color images, highlighting the importance of color in analyzing motion within static images.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Motion Analysis in Static Images

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Kunal Agrawal,
  • Vastsa S. Patel,
  • Reema Tharra,
  • Trung-Nghia Le,
  • Minh-Triet Tran,
  • Tam V. Nguyen

摘要

In this paper, we address the recognition of motion illusions in static images. To this end, we collect a new dataset containing images both with and without motion illusions. We then benchmark state-of-the-art deep learning models to determine the presence of illusions in the images. Additionally, we assess the role of color in the recognition process. The experimental results show that deep learning models are effective in identifying motion illusions, with superior performance on color images, highlighting the importance of color in analyzing motion within static images.