Using the dark channel prior as a complementary input improves single-image depth-from-defocus, giving strong results on synthetic NYU-v2 blur and qualitative generalization to real blur.
Self-supervised single-image depth estimation from focus and defocus clues,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Dark Channel-Assisted Depth-from-Defocus from a Single Image
Using the dark channel prior as a complementary input improves single-image depth-from-defocus, giving strong results on synthetic NYU-v2 blur and qualitative generalization to real blur.