Yifan Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yifan Zhang has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Wenmin Wang
School of Computer Science and Engineering, Macau University of Science and Technology, Macao 999078, China
4 shared publications - Honglei Li
School of Computer Science and Engineering, Macau University of Science and Technology, Macau, China
3 shared publications Guojun Liang
1 shared publicationHuan He
1 shared publication- Jianguo Wang1 shared publication
Shenyong Zhang
1 shared publication
Latest Publications
- 22 September 2026
- Published by Elsevier in Pattern Recognition Letters
- Vol. 210, 138-144
StyleDeOcc: Robust blind face inpainting with style-based de-occluder
- 22 September 2026
- Published by Elsevier in Pattern Recognition Letters
- Vol. 210, 138-144
StyleDeOcc: Robust blind face inpainting with style-based de-occluder
- 3 January 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 307
Insert Anyone: High-fidelity full-body photo insertion via dual-branch adapters
- 3 January 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 307
Insert Anyone: High-fidelity full-body photo insertion via dual-branch adapters
- 31 August 2024
- Published by Elsevier in Pattern Recognition
- Vol. 158
SwapInpaint2: Towards high structural consistency in identity-guided inpainting via background-preserving GAN inversion
- 31 August 2024
- Published by Elsevier in Pattern Recognition
- Vol. 158
SwapInpaint2: Towards high structural consistency in identity-guided inpainting via background-preserving GAN inversion
- Open Access
Recovery-Based Occluded Face Recognition by Identity-Guided Inpainting
Occlusion in facial photos poses a significant challenge for machine detection and recognition. Consequently, occluded face recognition for camera-captured images has emerged as a prominent and widely discussed topic in computer vision. The present standard face recognition methods have achieved remarkable performance in unoccluded face recognition but performed poorly when directly applied to occluded face datasets. The main reason lies in the absence of identity cues caused by occlusions. Therefore, a direct idea of recovering the occluded areas through an inpainting model has been proposed. However, existing inpainting models based on an encoder-decoder structure are limited in preserving inherent identity information. To solve the problem, we propose ID-Inpainter, an identity-guided face inpainting model, which preserves the identity information to the greatest extent through a more accurate identity sampling strategy and a GAN-like fusing network. We conduct recognition experiments on the occluded face photographs from the LFW, CFP-FP, and AgeDB-30 datasets, and the results indicate that our method achieves state-of-the-art performance in identity-preserving inpainting, and dramatically improves the accuracy of normal recognizers in occluded face recognition.
Open AccessRecovery-Based Occluded Face Recognition by Identity-Guided Inpainting
Occlusion in facial photos poses a significant challenge for machine detection and recognition. Consequently, occluded face recognition for camera-captured images has emerged as a prominent and widely discussed topic in computer vision. The present standard face recognition methods have achieved remarkable performance in unoccluded face recognition but performed poorly when directly applied to occluded face datasets. The main reason lies in the absence of identity cues caused by occlusions. Therefore, a direct idea of recovering the occluded areas through an inpainting model has been proposed. However, existing inpainting models based on an encoder-decoder structure are limited in preserving inherent identity information. To solve the problem, we propose ID-Inpainter, an identity-guided face inpainting model, which preserves the identity information to the greatest extent through a more accurate identity sampling strategy and a GAN-like fusing network. We conduct recognition experiments on the occluded face photographs from the LFW, CFP-FP, and AgeDB-30 datasets, and the results indicate that our method achieves state-of-the-art performance in identity-preserving inpainting, and dramatically improves the accuracy of normal recognizers in occluded face recognition.