OBIFormer: A Fast Attentive Denoising Framework for Oracle Bone Inscriptions
This addresses the challenge of automatic OBI recognition for anthropology and archaeology research, but it is incremental as it builds on existing transformer-based methods with efficiency improvements.
The paper tackles the problem of denoising severely degraded oracle bone inscriptions (OBIs) for automatic recognition, proposing OBIFormer, which achieves state-of-the-art performance in PSNR and SSIM metrics on synthetic and original datasets.
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.