Video Depth Anything adapts Depth Anything V2 to produce temporally consistent depth for arbitrarily long videos using a temporal attention head, an optical-flow-free gradient loss, and key-frame-based stitching.
Butler, Jonas Wulff, Garrett B
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
-
Video Depth Anything: Consistent Depth Estimation for Super-Long Videos
Video Depth Anything adapts Depth Anything V2 to produce temporally consistent depth for arbitrarily long videos using a temporal attention head, an optical-flow-free gradient loss, and key-frame-based stitching.