暗部噪声明显更难恢复，新方法让所有亮度区域同时提升
The Devil is in the Dark Pixels: Toward Brightness Bias-Robust Denoising
- 按亮度分段归一化误差，用动态加权优化各区域表现
- 暗区重建质量提升6倍，整体峰值信噪比最高增0.65 dB
- 无需额外参数，可直接替换现有模型损失函数
本文揭示图像去噪中一个被忽视的问题：在信号依赖型相机噪声模型下，暗区因信号强度衰减远快于噪声方差下降，导致信噪比先天偏低，细节恢复极为困难。然而，传统MSE训练的去噪器反而加剧这一问题——暗像素重建误差可达其每带噪声底限的6倍。根源在于信号依赖噪声放大亮区残差，且网络雅可比范数随亮度单调上升，致使亮区始终主导梯度更新。为此，我们提出亮度偏差鲁棒去噪（BBRD），一种即插即用的损失替代方案：将像素按亮度分带，以实测噪声方差归一化每带误差，并采用组分布鲁棒优化（Group-DRO）动态提升当前最差带权重，零额外参数与推理开销。在8种架构、2个数据集上，BBRD是13种对比方法中唯一实现所有亮度带同步提升的，于SIDD上暗带最高提升+0.45 dB，亮带+0.32 dB，整体PSNR提升+0.65 dB，尤其在最暗区域增益最大，对细节恢复意义重大。代码已开源。
原文摘要 · Abstract (English)
In this paper, we reveal an important yet overlooked problem in image denoising: under signal-dependent camera noise models, dark regions suffer from inherently low Signal-to-Noise Ratio (SNR), as signal intensity decays far faster than noise variance diminishes, making detail recovery in dark areas fundamentally challenging. Yet rather than compensating for this difficulty, MSE-trained denoisers exacerbate it -- reconstructing dark pixels up to 6x worse relative to their per-band noise floor. This bias stems from two compounding factors: signal-dependent noise inflates bright-pixel residuals, and the network's Jacobian norm increases monotonically with brightness. Together, these cause bright regions to chronically dominate gradient updates at the expense of dark ones. To this end, we propose Brightness Bias-Robust Denoising (BBRD), a drop-in replacement for MSE loss that partitions pixels into brightness bands, normalizes per-band error by empirical noise variance, and applies Group Distributionally Robust Optimization (Group-DRO) to dynamically upweight whichever band is currently worst, with zero additional parameters or inference cost. Across 8 architectures and 2 datasets in our experiments, BBRD is the only method among 13 tested alternatives that improves each brightness band simultaneously, achieving up to +0.45 dB on dark bands, +0.32 dB on bright bands, and +0.65 dB aggregate Peak Signal-to-Noise Ratio (PSNR) on SIDD, with the largest per-band gains in the darkest regions where detail recovery matters most. Code is available at https://github.com/xmed-lab/BBRD
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。