OmniMVS learns omnidirectional depth from multi-view fisheye images end-to-end and reports lower error than prior omnidirectional and stitched conventional stereo methods on synthetic benchmarks, with qualitative real-world demos.
A deep visual correspondence embedding model for stereo matching costs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
OmniMVS: End-to-End Learning for Omnidirectional Stereo Matching
OmniMVS learns omnidirectional depth from multi-view fisheye images end-to-end and reports lower error than prior omnidirectional and stitched conventional stereo methods on synthetic benchmarks, with qualitative real-world demos.