面向TDI CCD噪声建模的物理引导深度神经网络OA

Time-Delay Integration CCDs(TDI CCDs)are widely used in remote-sensing imaging.However,complex noise sources-including dark current,reset noise,and quantization noise-hinder accu-rate characterization of the signal-independent noise distribution of real sensors under low-light condi-tions.To address this challenge,a physics-guided deep neural network for TDI CCD noise modeling(PDNN)is proposed.Signal-independent noise is learned from dark-frame images and combined with signal-dependent noise modeled by a Poisson distribution,enabling accurate representation of the TDI CCD noise distribution in low-light scenes.First,a TDI CCD Noise Decoupling(TND)module de-composes dark-frame images into pixel-level noise with spatial independence.Next,a Gain and Multi-stage Adaptive(GMA)module,together with 1×1 convolutional layers in the TDI CCD Noise Model-ing(TNM)backbone,maps the initial noise into a distribution space that closely matches the true noise level while preserving pixel-wise independence.Finally,a Task Balanced Loss(TBL)dynamically ad-justs weighting factors to maintain training equilibrium,further improving performance.On a self-con-structed dataset,the proposed method achieves an average Kullback-Leibler divergence(AKLD)of 0.106 9,demonstrating substantial improvements over existing approaches.Moreover,PSNR and SSIM obtained from models trained with synthetic noisy images closely approximate those achieved with real data.Experimental results indicate that PDNN effectively characterizes the low-light noise distribu-tion of TDI CCDs,providing practical value for enhancing the visual quality of low-light remote-sensing imagery.