提出低通辅助监督机制，提升单张玻璃反射去除的泛化性能。
LowAux-RDNet: Low-Pass Residual Supervision with Scene-Balanced Real-World Training for Single-Image Reflection Removal
- 引入低通反射辅助目标，稳定低频约束并增强模型鲁棒性。
- 在五个数据集上平均达到27.546 dB PSNR，各项指标领先现有方法。
- 适用于真实场景复杂反射去除，尤其适合跨数据集应用研究者。
单图像反射去除旨在从透过玻璃拍摄的一幅图像中恢复出干净的透射层。本文基于RDNet构建显式分解流程，提出仅在训练阶段使用的低通反射辅助目标（LowAux）。原始残差目标仍为主要监督信号，而对预测与目标进行对称滤波后提供稳定的低频约束。进一步融合来自RRW的真实配对数据，扩大真实场景覆盖范围，提升跨数据集泛化能力。为避免因模型特定重缩放、填充、输出量化及度量代码导致的评估偏差，构建了基于CEILNet、Real20、Postcard、Objects和Wild的统一公开基准。在相同评估器下，所提系统在五数据集上宏平均达到27.546 dB PSNR、0.9220 SSIM、0.9751 NCC和0.004760 LMSE，PSNR、SSIM、NCC最高，LMSE最低，优于对比的公开检查点与内部变体。各数据集与定性分析表明，主要优势在于对多样化反射分布的更均衡表现，但Postcard中的清晰语义反射仍具挑战。
原文摘要 · Abstract (English)
Single-image reflection removal aims to recover a clean transmission layer from one image captured through glass. We study an explicit decomposition pipeline built on RDNet and introduce LowAux, a training-only low-pass reflection auxiliary objective. The original residual target remains the main reflection supervision, while symmetrically filtered prediction and target provide a stable low-frequency constraint. We further incorporate scene-balanced real pairs from RRW to broaden real-scene coverage and improve cross-dataset generalization. To avoid evaluation discrepancies caused by model-specific resizing, padding, output quantization, and metric code, we build a unified public benchmark over CEILNet, Real20, Postcard, Objects, and Wild. Under the same evaluator, the proposed system obtains a five-dataset macro average of 27.546 dB PSNR, 0.9220 SSIM, 0.9751 NCC, and 0.004760 LMSE, achieving the highest macro-average PSNR, SSIM, and NCC and the lowest LMSE among the compared public checkpoints and internal variants. Per-dataset and qualitative analyses show that the main benefit is a more balanced performance across diverse reflection distributions, while clear semantic reflections in Postcard remain challenging.
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。