AI model preview image
ZoeDepth is an image-to-image model that combines relative and metric depth information. It takes an input image and generates a corresponding depth map, which provides distance information for each pixel in the image. The model uses a combination of relative depth estimation, which estimates the depth differences between objects, and metric depth estimation, which estimates the absolute depth values. This approach allows the model to accurately estimate the depth of objects in the image and provide a more comprehensive depth map.

Use cases

ZoeDepth, an image-to-image model, offers a variety of exciting use cases for technical applications. One potential use case is in autonomous vehicle systems, where accurate depth information is crucial for safe navigation. ZoeDepth could be employed to generate depth maps from real-time camera inputs, enabling vehicles to perceive their surroundings in three dimensions and make informed decisions. Another use case is in augmented reality, where depth information can enhance the realism of virtual objects. By utilizing ZoeDepth, developers could improve the integration of virtual elements into the real world, creating more immersive and convincing experiences. Additionally, this model could find applications in robotics, where objects' depth perception is vital for obstacle avoidance and object manipulation. By leveraging ZoeDepth, robots could accurately gauge the distances to objects in their environment, enabling them to navigate and interact effectively. Furthermore, ZoeDepth may be valuable in computer vision and image processing tasks, such as object recognition and scene understanding. By utilizing the detailed depth maps generated by ZoeDepth, algorithms could have richer spatial information, allowing for more precise analysis and interpretation of images. In summary, ZoeDepth opens up possibilities for improved depth perception in autonomous vehicles, enhanced augmented reality experiences, more capable robots, and advanced computer vision applications. Potential products incorporating this model could include autonomous vehicles with enhanced perception systems, augmented reality headsets with improved object integration, advanced robot platforms with better spatial awareness, and computer vision algorithms with refined scene understanding capabilities.



Cost per run
Avg run time
Nvidia T4 GPU

Creator Models

Pix2pix Zero$?4,206
Night Enhancement$0.0104520,721
Mindall E$?1,645
Compositional Vsual Generation With Composable Diffusion Models Pytorch$0.01155774

Similar Models

Try it!

You can use this area to play around with demo applications that incorporate the Zoedepth model. These demos are maintained and hosted externally by third-party creators. If you see an error, message me on Twitter.

Currently, there are no demos available for this model.


Summary of this model and related resources.

Model NameZoedepth
ZoeDepth: Combining relative and metric depth
Model LinkView on Replicate
API SpecView on Replicate
Github LinkView on Github
Paper LinkView on Arxiv


How popular is this model, by number of runs? How popular is the creator, by the sum of all their runs?

Model Rank
Creator Rank


How much does it cost to run this model? How long, on average, does it take to complete a run?

Cost per Run$0.00275
Prediction HardwareNvidia T4 GPU
Average Completion Time5 seconds