Beyond Model Design: Data-Centric Training and Self-Ensemble for Gaussian Color Image Denoising

arXiv:2604.11468v1 Announce Type: new Abstract: This paper presents our solution to the NTIRE 2026 Image Denoising Challenge (Gaussian color image denoising at fixed noise level sigma = 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 sigma!=!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 imes 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 sigma!=!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.

Related

• UHD-GPGNet: UHD Video Denoising via Gaussian-Process-Guided Local Spatio-Temporal Modeling
• SAT: Selective Aggregation Transformer for Image Super-Resolution
• Degradation-Aware and Structure-Preserving Diffusion for Real-World Image Super-Resolution
• Dual-Branch Remote Sensing Infrared Image Super-Resolution
• NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Multi-Exposure Image Fusion in Dynamic Scenes (Track 2)
• NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild

Source: arXiv cs.CV | 2026-04-14