LFMT, a hybrid Mamba-Transformer network with unidirectional subspace scanning, reports new state-of-the-art light field super-resolution results on five benchmarks.
Occlusion-aware unsupervised learning of depth from 4-d light fields,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Exploring Non-Local Spatial-Angular Correlations with a Hybrid Mamba-Transformer Framework for Light Field Super-Resolution
LFMT, a hybrid Mamba-Transformer network with unidirectional subspace scanning, reports new state-of-the-art light field super-resolution results on five benchmarks.