- Python 85.4%
- Cuda 8.7%
- C++ 5.9%
| Filename | Latest commit message | Latest commit date |
|---|---|---|
| SteleSR | ||
| README.md | ||
SteleSR
Bridging the Semantic-Visual Gap: A Universal Super-Resolution Framework for Ancient Stele Inscriptions
Ancient stele inscriptions face irreversible information loss due to millennia of environmental degradation. This paper presents the first systematic effort to address the task of Stele Inscription Text Image Super-Resolution. General-purpose models often suffer from a "semantic-visual imbalance" in this domain, where a lack of structural priors leads to spurious topological connections that render restored text illegible. To resolve this, we propose SISTR, the first systematic benchmark and progressive paradigm that bridges the gap between synthetic noise and real-world damage via LLM-driven structural decoupling and LVM-guided style injection. Furthermore, we introduce SteleSR, a universal restoration framework that integrates Edge-aware and Text Prior losses into diverse super-resolution backbones to ensure both visual authenticity and semantic legibility. Extensive evaluations across semantic and structural metrics demonstrate that SteleSR consistently enhances various models, establishing a pioneering standard for the high-fidelity digital preservation of historical artifacts.
Overview
Real-World SR Results
Environment
- PyTorch >= 1.7
- BasicSR == 1.3.4.9
How To Test
The HAT model is used as an example here.
- Refer to
./options/test/HATfor the configuration files of the models to be evaluated. - Prepare the testing dataset and pretrained checkpoints before inference.
- The testing results will be saved in the
./resultsdirectory.
python basicsr/test.py -opt options/test/HAT/HAT_SRx4_ImageNet-LR.yml
How To Train
The HAT model is used as an example here.
- Refer to
./options/train/HATfor the training configuration files. - Prepare the training datasets before starting training.
- Training logs and checkpoints will be saved in the
./experimentsdirectory.
Stage 1: Training on SISTR-Syn
python basicsr/train.py -opt options/train/HAT/train_HAT-L_SRx4_ImageNet_from_scratch_test.yml
Stage 2: Finetuning on SISTR-LVM
python basicsr/train.py -opt options/train/HAT/train_HAT-L_SRx4_finetune_from_ImageNet_pretrain_test.yml