SuperF performs multi-image super-resolution up to 8x by jointly optimizing a shared neural implicit representation and sub-pixel frame alignments from low-resolution bursts without any high-resolution training data.
Guided depth super-resolution by deep anisotropic diffusion
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SuperF: Neural Implicit Fields for Multi-Image Super-Resolution
SuperF performs multi-image super-resolution up to 8x by jointly optimizing a shared neural implicit representation and sub-pixel frame alignments from low-resolution bursts without any high-resolution training data.