Ultra-High-Definition Dynamic Multi-Exposure Image Fusion via Infinite Pixel Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913613981155328 |
|---|---|
| author | Chen, Xingchi Zheng, Zhuoran Li, Xuerui Chen, Yuying Wang, Shu Ren, Wenqi |
| author_facet | Chen, Xingchi Zheng, Zhuoran Li, Xuerui Chen, Yuying Wang, Shu Ren, Wenqi |
| contents | With the continuous improvement of device imaging resolution, the popularity of Ultra-High-Definition (UHD) images is increasing. Unfortunately, existing methods for fusing multi-exposure images in dynamic scenes are designed for low-resolution images, which makes them inefficient for generating high-quality UHD images on a resource-constrained device. To alleviate the limitations of extremely long-sequence inputs, inspired by the Large Language Model (LLM) for processing infinitely long texts, we propose a novel learning paradigm to achieve UHD multi-exposure dynamic scene image fusion on a single consumer-grade GPU, named Infinite Pixel Learning (IPL). The design of our approach comes from three key components: The first step is to slice the input sequences to relieve the pressure generated by the model processing the data stream; Second, we develop an attention cache technique, which is similar to KV cache for infinite data stream processing; Finally, we design a method for attention cache compression to alleviate the storage burden of the cache on the device. In addition, we provide a new UHD benchmark to evaluate the effectiveness of our method. Extensive experimental results show that our method maintains high-quality visual performance while fusing UHD dynamic multi-exposure images in real-time (>40fps) on a single consumer-grade GPU. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_11685 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Ultra-High-Definition Dynamic Multi-Exposure Image Fusion via Infinite Pixel Learning Chen, Xingchi Zheng, Zhuoran Li, Xuerui Chen, Yuying Wang, Shu Ren, Wenqi Computer Vision and Pattern Recognition With the continuous improvement of device imaging resolution, the popularity of Ultra-High-Definition (UHD) images is increasing. Unfortunately, existing methods for fusing multi-exposure images in dynamic scenes are designed for low-resolution images, which makes them inefficient for generating high-quality UHD images on a resource-constrained device. To alleviate the limitations of extremely long-sequence inputs, inspired by the Large Language Model (LLM) for processing infinitely long texts, we propose a novel learning paradigm to achieve UHD multi-exposure dynamic scene image fusion on a single consumer-grade GPU, named Infinite Pixel Learning (IPL). The design of our approach comes from three key components: The first step is to slice the input sequences to relieve the pressure generated by the model processing the data stream; Second, we develop an attention cache technique, which is similar to KV cache for infinite data stream processing; Finally, we design a method for attention cache compression to alleviate the storage burden of the cache on the device. In addition, we provide a new UHD benchmark to evaluate the effectiveness of our method. Extensive experimental results show that our method maintains high-quality visual performance while fusing UHD dynamic multi-exposure images in real-time (>40fps) on a single consumer-grade GPU. |
| title | Ultra-High-Definition Dynamic Multi-Exposure Image Fusion via Infinite Pixel Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.11685 |