A dual-branch transformer with masked joint attention completes dense metric depth from sparse dToF sensors, trained entirely on synthetic data and generalizing zero-shot to real devices.
Proceedings of the European Conference on Computer Vision (ECCV) Workshops , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Dense Metric Depth Completion from Sparse Direct Time-of-Flight Sensors
A dual-branch transformer with masked joint attention completes dense metric depth from sparse dToF sensors, trained entirely on synthetic data and generalizing zero-shot to real devices.