Meet-in-the-middle: Multi-scale upsampling and matching for cross-resolution face recognition

Creative Commons License

Grm K., Ozata B. K., Struc V., Ekenel H. K.

2023 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops, WACVW 2023, Hawaii, United States Of America, 3 - 07 January 2023, pp.120-129 identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/wacvw58289.2023.00017
  • City: Hawaii
  • Country: United States Of America
  • Page Numbers: pp.120-129
  • Istanbul Technical University Affiliated: Yes


In this paper, we aim to address the large domain gap between high-resolution face images, e.g., from professional portrait photography, and low-quality surveillance images, e.g., from security cameras. Establishing an identity match between disparate sources like this is a classical surveillance face identification scenario, which continues to be a challenging problem for modern face recognition techniques. To that end, we propose a method that combines face super-resolution, resolution matching, and multi-scale template accumulation to reliably recognize faces from long-range surveillance footage, including from low quality sources. The proposed approach does not require training or fine-tuning on the target dataset of real surveillance images. Extensive experiments show that our proposed method is able to outperform even existing methods fine-tuned to the SCFace dataset.