S2S-ST reconstructs dense spatial gene expression from 25% sampled spots using self-supervision plus natural-image co-training, and reports better MAE and SSIM than TESLA, BayesSpace, and DIST on eight Xenium samples.
, author Triandafillou, C.G
1 Pith paper cite this work, alongside 10 external citations. Polarity classification is still indexing.
1
Pith paper citing it
10
external citations · OpenAlex
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Sparser2Sparse: Single-shot Sparser-to-Sparse Learning for Spatial Transcriptomics Imputation with Natural Image Co-learning
S2S-ST reconstructs dense spatial gene expression from 25% sampled spots using self-supervision plus natural-image co-training, and reports better MAE and SSIM than TESLA, BayesSpace, and DIST on eight Xenium samples.