AI RESEARCH
Beyond Model Design: Data-Centric Training and Self-Ensemble for Gaussian Color Image Denoising
arXiv CS.CV
•
ArXi:2604.11468v1 Announce Type: new 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