SARU unifies shadow detection via a dual-branch neural network and removal via a training-free physical algorithm on single images, introduces two new benchmarks, and reports state-of-the-art detection plus fast removal with SRI near 0.9.
IEEE Trans
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
-
SARU: A Shadow-Aware and Removal Unified Framework for Remote Sensing Images with New Benchmarks
SARU unifies shadow detection via a dual-branch neural network and removal via a training-free physical algorithm on single images, introduces two new benchmarks, and reports state-of-the-art detection plus fast removal with SRI near 0.9.