MG-SpaIR introduces a multi-grade sparse-guided implicit neural representation framework for training-data-free image restoration that outperforms Deep Image Prior on mixed-degradation benchmarks.
In: Advances in Neural Information Processing Systems (NeurIPS) (2022)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MG-SpaIR: Multi-grade Sparse-guided Implicit Representation for Training-Data-Free Image Restoration
MG-SpaIR introduces a multi-grade sparse-guided implicit neural representation framework for training-data-free image restoration that outperforms Deep Image Prior on mixed-degradation benchmarks.