直接在原始拜耳域去雨，效果更好速度更快。
$\mathbf{R}^3$: Reconstruction, Raw, and Rain: Deraining Directly in the Bayer Domain
- 在原始拜耳图像上直接去雨，避免了图像处理过程中的信息损失。
- 相比传统方法，峰值信噪比提升0.99 dB，感知评分提高1.2%。
- 适合需要高保真图像重建的科研与工业应用。
图像重建在多个领域至关重要。现有大多数重建网络在经过图像信号处理（ISP）后的sRGB图像上训练，但这一过程会不可逆地混合颜色、压缩动态范围并模糊细节。本文以去雨问题为例，证明这些损失可避免，并展示在原始拜耳域直接学习能获得更优重建效果。为此，我们：(i) 比较了后ISP与拜耳域重建流程；(ii) 构建了首个公开的真实雨天场景数据集Raw-Rain，包含12位拜耳与位深匹配的sRGB图像；(iii) 提出信息保全评分（ICS），一种与人类感知更一致的颜色无关度量指标。在测试集上，我们的拜耳域模型使sRGB结果提升最高达+0.99 dB PSNR和+1.2% ICS，且计算量减半，仅需一半的GFLOPs。结果支持低层视觉中采用ISP-last范式，并为端到端可学习相机流水线开辟道路。
原文摘要 · Abstract (English)
Image reconstruction from corrupted images is crucial across many domains. Most reconstruction networks are trained on post-ISP sRGB images, even though the image-signal-processing pipeline irreversibly mixes colors, clips dynamic range, and blurs fine detail. This paper uses the rain degradation problem as a use case to show that these losses are avoidable, and demonstrates that learning directly on raw Bayer mosaics yields superior reconstructions. To substantiate the claim, we (i) evaluate post-ISP and Bayer reconstruction pipelines, (ii) curate Raw-Rain, the first public benchmark of real rainy scenes captured in both 12-bit Bayer and bit-depth-matched sRGB, and (iii) introduce Information Conservation Score (ICS), a color-invariant metric that aligns more closely with human opinion than PSNR or SSIM. On the test split, our raw-domain model improves sRGB results by up to +0.99 dB PSNR and +1.2% ICS, while running faster with half of the GFLOPs. The results advocate an ISP-last paradigm for low-level vision and open the door to end-to-end learnable camera pipelines.
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。