TM-BSN introduces triangular-masked convolutions that align blind spots with diamond-shaped noise correlations from camera demosaicing, enabling stronger self-supervised denoising at full resolution without downsampling.
Image denoising by sparse 3-d transform- domain collaborative filtering.IEEE Transactions on image processing, 16(8):2080–2095
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TM-BSN: Triangular-Masked Blind-Spot Network for Real-World Self-Supervised Image Denoising
TM-BSN introduces triangular-masked convolutions that align blind spots with diamond-shaped noise correlations from camera demosaicing, enabling stronger self-supervised denoising at full resolution without downsampling.