This paper presents our solution to the NTIRE 2026 Image Denoising Challenge (Gaussian color image denoising at fixed noise level $σ= 50$). Rather than proposing a new restoration backbone, we revisit the performance boundary of the mature Restormer architecture from two complementary directions: stronger data-centric training and more complete Test-Time capability release. Starting from the public Restormer $σ\!=\!50$ baseline, we expand the standard multi-dataset training recipe with larger and more diverse public image corpora and organize optimization into two stages. At inference, we apply $\times 8$ geometric self-ensemble to further release model capacity. A TLC-style local inference wrapper is retained for implementation consistency; however, systematic ablation reveals its quantitative contribution to be negligible in this setting. On the challenge validation set of 100 images, our final submission achieves 30.762 dB PSNR and 0.861 SSIM, improving over the public Restormer $σ\!=\!50$ pretrained baseline by up to 3.366 dB PSNR. Ablation studies show that the dominant gain originates from the expanded training corpus and the two-stage optimization schedule, and self-ensemble provides marginal but consistent improvement.

翻译：本文提出我们针对NTIRE 2026图像去噪挑战赛（固定噪声水平σ=50的高斯彩色图像去噪）的解决方案。不同于提出新的修复主干网络，我们从两个互补方向重新审视成熟Restormer架构的性能边界：更强化的数据中心训练策略与更完备的测试时能力释放。基于公开的Restormer σ=50基线模型，我们通过引入更大规模且更多样化的公开图像语料库扩展标准多数据集训练方案，并设计两阶段优化流程。在推理阶段，采用×8几何自集成进一步释放模型容量。为保持实现一致性，保留TLC风格局部推理封装器，但系统消融实验表明该组件在此设置下的定量贡献可忽略。在包含100张图像的挑战验证集上，最终提交结果达到30.762 dB PSNR和0.861 SSIM，相较公开的Restormer σ=50预训练基线模型提升高达3.366 dB PSNR。消融研究表明，主要性能增益源于扩展训练语料库与两阶段优化策略，而自集成方法贡献了微小但一致的提升。