Depth Estimation
On‑device monocular depth estimation with TFLite
A sample app for Ubuntu integrating monocular depth‑estimation models (Depth‑Anything, Depth‑Anything‑V2, Depth‑Anything‑V3, Midas) via TFLite Runtime. It uses GStreamer for input video and provides a minimal web interface to stream a depth heatmap suitable for embedded applications.
1. Choose a compatible model
2. Get source code and dependencies
3. Build and run app
Compatible Models
Depth-Anything
Deep Convolutional Neural Network model for depth estimation.
Depth-Anything-V2
Deep Convolutional Neural Network model for depth estimation.
Depth-Anything-V3
Deep Convolutional Neural Network model for depth estimation.
Midas-V2
Deep Convolutional Neural Network model for depth estimation.
Information
Operating System
Ubuntu 24.04+Language
PythonRuntime
TFLite
Use Case
Depth Estimation
Join Us on Slack
Join our growing community of 2000+ developers in the AI Hub Slack Channel building the future of AI
Join Now