Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.11181 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917233704304640 |
|---|---|
| author | Martini, Luca Zolezzi, Daniele Iacono, Saverio Vercelli, Gianni Viardo |
| author_facet | Martini, Luca Zolezzi, Daniele Iacono, Saverio Vercelli, Gianni Viardo |
| contents | The reconstruction of low-resolution football broadcast images presents a significant challenge in sports broadcasting, where detailed visuals are essential for analysis and audience engagement. This study introduces a multi-stage generative upscaling framework leveraging Diffusion Models to enhance degraded images, transforming inputs as small as $64 \times 64$ pixels into high-fidelity $1024 \times 1024$ outputs. By integrating an image-to-image pipeline, ControlNet conditioning, and LoRA fine-tuning, our approach surpasses traditional upscaling methods in restoring intricate textures and domain-specific elements such as player details and jersey logos. The custom LoRA is trained on a custom football dataset, ensuring adaptability to sports broadcast needs. Experimental results demonstrate substantial improvements over conventional models, with ControlNet refining fine details and LoRA enhancing task-specific elements. These findings highlight the potential of diffusion-based image reconstruction in sports media, paving the way for future applications in automated video enhancement and real-time sports analytics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_11181 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-Stage Generative Upscaler: Reconstructing Football Broadcast Images via Diffusion Models Martini, Luca Zolezzi, Daniele Iacono, Saverio Vercelli, Gianni Viardo Computer Vision and Pattern Recognition Artificial Intelligence The reconstruction of low-resolution football broadcast images presents a significant challenge in sports broadcasting, where detailed visuals are essential for analysis and audience engagement. This study introduces a multi-stage generative upscaling framework leveraging Diffusion Models to enhance degraded images, transforming inputs as small as $64 \times 64$ pixels into high-fidelity $1024 \times 1024$ outputs. By integrating an image-to-image pipeline, ControlNet conditioning, and LoRA fine-tuning, our approach surpasses traditional upscaling methods in restoring intricate textures and domain-specific elements such as player details and jersey logos. The custom LoRA is trained on a custom football dataset, ensuring adaptability to sports broadcast needs. Experimental results demonstrate substantial improvements over conventional models, with ControlNet refining fine details and LoRA enhancing task-specific elements. These findings highlight the potential of diffusion-based image reconstruction in sports media, paving the way for future applications in automated video enhancement and real-time sports analytics. |
| title | Multi-Stage Generative Upscaler: Reconstructing Football Broadcast Images via Diffusion Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2503.11181 |