OBIFormer: A Fast Attentive Denoising Framework for Oracle Bone Inscriptions
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909584164126720 |
|---|---|
| author | Li, Jinhao Chen, Zijian Chen, Tingzhu Liu, Zhiji Wang, Changbo |
| author_facet | Li, Jinhao Chen, Zijian Chen, Tingzhu Liu, Zhiji Wang, Changbo |
| contents | Oracle bone inscriptions (OBIs) are the earliest known form of Chinese characters and serve as a valuable resource for research in anthropology and archaeology. However, most excavated fragments are severely degraded due to thousands of years of natural weathering, corrosion, and man-made destruction, making automatic OBI recognition extremely challenging. Previous methods either focus on pixel-level information or utilize vanilla transformers for glyph-based OBI denoising, which leads to tremendous computational overhead. Therefore, this paper proposes a fast attentive denoising framework for oracle bone inscriptions, i.e., OBIFormer. It leverages channel-wise self-attention, glyph extraction, and selective kernel feature fusion to reconstruct denoised images precisely while being computationally efficient. Our OBIFormer achieves state-of-the-art denoising performance for PSNR and SSIM metrics on synthetic and original OBI datasets. Furthermore, comprehensive experiments on a real oracle dataset demonstrate the great potential of our OBIFormer in assisting automatic OBI recognition. The code will be made available at https://github.com/LJHolyGround/OBIFormer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_13524 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OBIFormer: A Fast Attentive Denoising Framework for Oracle Bone Inscriptions Li, Jinhao Chen, Zijian Chen, Tingzhu Liu, Zhiji Wang, Changbo Computer Vision and Pattern Recognition Oracle bone inscriptions (OBIs) are the earliest known form of Chinese characters and serve as a valuable resource for research in anthropology and archaeology. However, most excavated fragments are severely degraded due to thousands of years of natural weathering, corrosion, and man-made destruction, making automatic OBI recognition extremely challenging. Previous methods either focus on pixel-level information or utilize vanilla transformers for glyph-based OBI denoising, which leads to tremendous computational overhead. Therefore, this paper proposes a fast attentive denoising framework for oracle bone inscriptions, i.e., OBIFormer. It leverages channel-wise self-attention, glyph extraction, and selective kernel feature fusion to reconstruct denoised images precisely while being computationally efficient. Our OBIFormer achieves state-of-the-art denoising performance for PSNR and SSIM metrics on synthetic and original OBI datasets. Furthermore, comprehensive experiments on a real oracle dataset demonstrate the great potential of our OBIFormer in assisting automatic OBI recognition. The code will be made available at https://github.com/LJHolyGround/OBIFormer. |
| title | OBIFormer: A Fast Attentive Denoising Framework for Oracle Bone Inscriptions |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.13524 |