提出新模型实现4K/8K图像实时去雾，训练快5倍且内存更低。
UHD Image Dehazing via anDehazeFormer with Atmospheric-aware KV Cache
- 用自适应归一化加速训练，限制参数表达范围提升稳定性。
- 基于物理雾霾模型设计动态KV缓存，保留关键特征减少冗余。
- 可在RTX4090上每秒处理50张高清图，适合高分辨率图像去雾场景。
本文提出一种高效的视觉Transformer框架，用于超高清（UHD）图像去雾，解决了现有方法训练慢、内存高的问题。提出两项创新：1）受nGPT启发的自适应归一化机制，使网络在参数表达受限条件下实现超快且稳定的训练；2）设计了基于大气散射模型的KV缓存机制，动态优化特征保留。该架构使训练收敛速度提升5倍，降低内存开销，在RTX4090 GPU上实现每秒处理50张高分辨率图像的实时处理能力。实验表明，该方法在4K/8K图像复原任务中保持了顶尖去雾质量，并显著提升计算效率。此外，通过集成梯度归因图提供可解释性分析。代码已公开。
原文摘要 · Abstract (English)
In this paper, we propose an efficient visual transformer framework for ultra-high-definition (UHD) image dehazing that addresses the key challenges of slow training speed and high memory consumption for existing methods. Our approach introduces two key innovations: 1) an \textbf{a}daptive \textbf{n}ormalization mechanism inspired by the nGPT architecture that enables ultra-fast and stable training with a network with a restricted range of parameter expressions; and 2) we devise an atmospheric scattering-aware KV caching mechanism that dynamically optimizes feature preservation based on the physical haze formation model. The proposed architecture improves the training convergence speed by \textbf{5 $\times$} while reducing memory overhead, enabling real-time processing of 50 high-resolution images per second on an RTX4090 GPU. Experimental results show that our approach maintains state-of-the-art dehazing quality while significantly improving computational efficiency for 4K/8K image restoration tasks. Furthermore, we provide a new dehazing image interpretable method with the help of an integrated gradient attribution map. Our code can be found here: https://anonymous.4open.science/r/anDehazeFormer-632E/README.md.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。