DocDiff icon indicating copy to clipboard operation
DocDiff copied to clipboard

ACM Multimedia 2023: DocDiff: Document Enhancement via Residual Diffusion Models. Also contains 1597 red seals in Chinese scenes, along with their corresponding binary masks.

Results 5 DocDiff issues
Sort by recently updated
recently updated
newest added

This issue is coming during inference phase of this model for every image File "/home/mepluser1/rahul_hanot/try_new/DocDiff/model/DocDiff.py", line 315, in forward x = torch.cat((x, s), dim=1) RuntimeError: Sizes of tensors must match...

help wanted

How can we convert these models into ONNX format and deploy them could you please provide code for ONNX inference

这个开源项目提供了一些生成噪声的预处理流程。 https://github.com/sparkfish/shabby-pages 他提供了一个pipeline,用于合成各种噪声的图片。 ![Article_Hero_Picture_Shadow.png](https://github.com/Royalvice/DocDiff/assets/110762732/2b9c01ce-b64b-412e-94df-d14820945340)