Jul 2026
LoTA-N2N: Local Trace Adaptation for Zero-Shot Self-Supervised Image Denoising
LoTA-N2N demonstrates that estimated local interaction and spatial cancellation control provide effective design principles for single-image self-supervised denoising without paired clean targets, repeated acquisitions, or a predefined re-corruption model.
Jintong Hu, Bin Xia, Jun-Lin Liu et al.
· arXiv.org · 0 citations