Depth-Anything TensorRT

Depth estimation is the task of measuring the distance of each pixel relative to the camera. This repo hosts a C++ and python implementation of the Depth-Anything Monocular Depth Estimation model, leveraging the TensorRT API for efficient real-time inference.

⏱️ Performance

The inference time includes the pre-preprocessing and post-processing stages:

Device	Model	Model Input (WxH)	Image Resolution (WxH)	Inference Time(ms)
RTX4090	Depth-Anything-S	518x518	1280x720	3
RTX4090	Depth-Anything-B	518x518	1280x720	6
RTX4090	Depth-Anything-L	518x518	1280x720	12

Note that the inference was conducted using FP16 precision, with a warm-up period of 10 frames, and the reported time corresponds to the last inference.

🚀 Usage

Linux:

# infer image
./depth-anything-tensorrt depth_anything_vitb14.engine test.jpg
# infer folder(images)
./depth-anything-tensorrt depth_anything_vitb14.engine data
# infer video
./depth-anything-tensorrt depth_anything_vitb14.engine test.mp4 # the video path

Windows:

# infer image
./depth-anything-tensorrt.exe depth_anything_vitb14.engine test.jpg
# infer folder(images)
./depth-anything-tensorrt.exe depth_anything_vitb14.engine data
# infer video
./depth-anything-tensorrt.exe depth_anything_vitb14.engine test.mp4 # the video path

🛠️ Setup

Refer to our docs/INSTALL.md for detailed installation instructions.

👏 Acknowledgement

This project is based on the following projects:

• Depth-Anything - Unleashing the Power of Large-Scale Unlabeled Data.
• TensorRT - TensorRT samples and api documentation.