5.5. Dense Depth Estimation

By inputting a single frame of image and point cloud, the PromptDA algorithm is utilized to generate a dense depth map based on the image resolution.
Below demonstrates the effects exhibited by models of different sizes.

5.5.1. PromptDA-vitlarge

The computational platforms currently supported by this network are listed in the table below:

Computing Platform	General X86 Architecture Computers	Radxa ROCK5B+	OrangePi 5 Ultra	NVIDIA Jetson Orin Nano Super	NVIDIA Jetson AGX Orin	D-Robotics RDK X5
	●	●	●	●	●	○
Model Size	1360M
Sensor	AC1

The following video demonstrates the offline dense depth estimation effect of this network on a supported computing platform for an indoor scene.

Video Data: Library
Source Code: AC1 Dense Depth vitlarge

5.5.2. PromptDA-vitsmall

The computational platforms currently supported by this network are listed in the table below:

Computing Platform	General X86 Architecture Computers	Radxa ROCK5B+	OrangePi 5 Ultra	NVIDIA Jetson Orin Nano Super	NVIDIA Jetson AGX Orin	D-Robotics RDK X5
	●	●	●	●	●	○
Model Size	100M
Sensor	AC1

The following video demonstrates the offline dense depth estimation effect of this network on a supported computing platform for an indoor scene.

Video Data: Library
Source Code: AC1 Dense Depth vitsmall