Zoedepth Nyu
ZoeDepth is a model for monocular depth estimation, specifically fine-tuned on the NYU dataset, capable of zero-shot transfer and metric depth estimation.
Downloads 1,279
Release Time : 4/30/2024
Model Overview
ZoeDepth extends the DPT framework for metric (absolute) depth estimation, achieving state-of-the-art results. The model can perform monocular depth estimation in a zero-shot manner and outputs depth information with actual metric values.
Model Features
Zero-shot transfer
Capable of performing depth estimation without task-specific training data.
Metric depth estimation
Can output actual metric depth values, not just relative depth.
Based on the DPT framework
Extends the DPT framework, combining the advantages of relative and metric depth estimation.
Model Capabilities
Monocular depth estimation
Zero-shot transfer
Metric depth output
Use Cases
Computer vision
Indoor scene depth estimation
The model fine-tuned on the NYU dataset is particularly suitable for depth estimation in indoor scenes.
Can accurately estimate depth information in indoor environments.
3D scene reconstruction
Can be used to reconstruct 3D scenes from a single image.
Provides precise depth information to support 3D reconstruction.
Featured Recommended AI Models