轻量CNN在低光图像恢复上逼近SwinIR性能，训练更快更省资源。
Is Architectural Complexity Always the Answer? A Case Study on SwinIR vs. an Efficient CNN
- 用标准轻量CNN对比SwinIR，验证架构复杂度是否必须
- CNN达37.4dB PSNR，仅需10轮训练，比SwinIR快12倍
- 模型大小仅为SwinIR的1/55，适合资源受限场景
低光图像中同时恢复高频细节与抑制严重噪声是计算机视觉中的长期挑战。尽管基于Transformer的SwinIR模型在性能上达到前沿水平，但其高计算成本限制了实际应用。本文通过对比SwinIR与标准轻量卷积神经网络（CNN）在此任务上的表现，研究性能与效率之间的权衡。实验结果表明，虽然SwinIR取得更高峰值性能（PSNR 39.03 dB），但轻量CNN在仅10个训练周期后即达到37.4 dB的竞争力结果，且模型规模比SwinIR小超过55倍。该研究证明，标准CNN可在显著降低计算开销的前提下实现接近顶尖的性能，为资源受限的实际应用场景提供了有力方案。
原文摘要 · Abstract (English)
The simultaneous restoration of high-frequency details and suppression of severe noise in low-light imagery presents a significant and persistent challenge in computer vision. While large-scale Transformer models like SwinIR have set the state of the art in performance, their high computational cost can be a barrier for practical applications. This paper investigates the critical trade-off between performance and efficiency by comparing the state-of-the-art SwinIR model against a standard, lightweight Convolutional Neural Network (CNN) on this challenging task. Our experimental results reveal a nuanced but important finding. While the Transformer-based SwinIR model achieves a higher peak performance, with a Peak Signal-to-Noise Ratio (PSNR) of 39.03 dB, the lightweight CNN delivers a surprisingly competitive PSNR of 37.4 dB. Crucially, the CNN reached this performance after converging in only 10 epochs of training, whereas the more complex SwinIR model required 132 epochs. This efficiency is further underscored by the model's size; the CNN is over 55 times smaller than SwinIR. This work demonstrates that a standard CNN can provide a near state-of-the-art result with significantly lower computational overhead, presenting a compelling case for its use in real-world scenarios where resource constraints are a primary concern.
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。