CodingHomo combines codec motion vectors with masked image features to estimate homographies, setting a new state of the art on the CA-unsup and GHOF benchmarks within its small-baseline scope.
Homography loss for monocular 3d object detection,
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
-
CodingHomo: Bootstrapping Deep Homography With Video Coding
CodingHomo combines codec motion vectors with masked image features to estimate homographies, setting a new state of the art on the CA-unsup and GHOF benchmarks within its small-baseline scope.