mbcnn-uhdm-demoireing is an open-weight model from runningTurtle, released under MIT License. Its published files total 113.6 MB.
Two inference-only MBCNN checkpoints reproduced with the standalone PyTorch implementation in The epoch-110 model is test-selected because the official UHDM test set was used for center-crop checkpoint selection.
Model Card
By runningTurtle, published under mit, revision 10fcffd17118.
Two inference-only MBCNN checkpoints reproduced with the standalone PyTorch implementation in The epoch-110 model is test-selected because the official UHDM test set was used for center-crop checkpoint selection. The epoch-150 model is provided as the fixed-schedule result. Both full evaluations use all 500 test images, direct FP32 full-resolution inference without tiling, ESDNet-style padding, full-RGB PSNR, and valid-window SSIM. LPIPS was not computed. The files contain only model parameters in safetensors format. Training optimizer and scaler states are intentionally omitted. See the resource repository for code, exact configuration, per-image metrics, licensing, and attribution.
Read runningTurtle's full model card
MBCNN trained on UHDM
Two inference-only MBCNN checkpoints reproduced with the standalone PyTorch
implementation in
Running-Turtle1/demoireing-resources.
| File | Epoch | Selection | Full UHDM PSNR | Full UHDM SSIM |
|---|---|---|---|---|
uhdm/best_epoch110/model.safetensors |
110 | Best PSNR on 100 center crops | 20.223574 | 0.771880 |
uhdm/last_epoch150/model.safetensors |
150 | Fixed final epoch | 20.002245 | 0.768795 |
The epoch-110 model is test-selected because the official UHDM test set was used for center-crop checkpoint selection. The epoch-150 model is provided as the fixed-schedule result. Both full evaluations use all 500 test images, direct FP32 full-resolution inference without tiling, ESDNet-style padding, full-RGB PSNR, and valid-window SSIM. LPIPS was not computed.
The files contain only model parameters in safetensors format. Training optimizer and scaler states are intentionally omitted. See the resource repository for code, exact configuration, per-image metrics, licensing, and attribution.
Identity and Version
- Repository
- running-Turtle/mbcnn-uhdm-demoireing
- Publisher
- runningTurtle
- Task
- Not stated by the source
- Modality
- Other
- Library
- pytorch
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 10fcffd17118e94da4873ffcf98a741bb7f5df83
- First published
- 2026-10-07
- Last updated
- 2026-10-07
Files and Weights
4 files, 113.6 MB in total. The weights are 2 files totalling 113.6 MB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| uhdm/best_epoch110/model.safetensors | Weights | 56.8 MB | 0a171b1deb42 |
| uhdm/last_epoch150/model.safetensors | Weights | 56.8 MB | ba39933410c9 |
| README.md | Documentation | 1.2 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- mit
- Access
- Open weights, no gate
- Download size
- 113.6 MB
Released by runningTurtle through its official repository on Hugging Face. Read the license.
Built From
- Trained on (disclosed) UHDM
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 113.6 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About mbcnn-uhdm-demoireing
Can I use mbcnn-uhdm-demoireing commercially?
Yes. mbcnn-uhdm-demoireing is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.