Prior Depth Anything unifies depth completion, super-resolution, and inpainting by aligning a monocular prediction to partial metric priors pixel by pixel, then refining with a conditioned network.
Arkitscenes: A diverse real-world dataset for 3d indoor scene understanding using mobile rgb-d data
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
-
Depth Anything with Any Prior
Prior Depth Anything unifies depth completion, super-resolution, and inpainting by aligning a monocular prediction to partial metric priors pixel by pixel, then refining with a conditioned network.