MetricGold fine-tunes Stable Diffusion's latent space on log-scaled synthetic depth to predict metric depth from single images, claiming efficient zero-shot generalization without reported benchmarks.
Repurposing diffusion-based image generators for monocular depth estimation, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
MetricGold: Leveraging Text-To-Image Latent Diffusion Models for Metric Depth Estimation
MetricGold fine-tunes Stable Diffusion's latent space on log-scaled synthetic depth to predict metric depth from single images, claiming efficient zero-shot generalization without reported benchmarks.