Depth Scanner 2

Parameters

Model

The underlying depth estimation model. The native video depth model processes multiple frames simultaneously and results are more stable over time.

Memory Optimization (only for native video depth model)

Save some memory by running some of the ai computations sequentially instead of in parallel.

Base Resolution

The image resolution on which the depth map is computed.

Edges Enhancement

Enhances edge details. The higher the setting the stronger the filter. A high value may give inaccurate results.

Subpixel smoothing

Will reduce flickering between frames at the cost of edge sharpness.

Mapping Mode

Define, how the computed depth will be mapped to the 0-1 range for displaying.

Raw

This is the raw depth prediction. Use this for consistent results between frames.

Normalize

Scale the computed depth to the 0-1 range. This can introduce flickering on image sequences / videos.

Guided

Set (and keyframe) the two points Near Guide Point and Far Guide Point as well the Near and Far values to define which parts of the image correspond to which depth. This can reduce flickering as it will attached fixed depth values to fixed objects in the scene and make sure all values inbetween are interpolated accordingly.

Mode

Choose between “Depth Map” and “Slicing”. “Depth Map” outputs the pure depth, whilst slicing lets you select parts of the images based on depth.

Colormap (only if “Depth Map”)

Will map the depth values to the color map choosen.

Minimum (only if “Slicing”)

The near plane to cut.

Maximum (only if “Slicing”)

The far plane to cut.

Backend & Performance

Hardware Acceleration (on GPU version of the plugin only)

Run calculations on the GPU. This will give massive speedups compared to CPU mode.

Lower Precision

Compute with reduced precision if possible. This can save up to half of the memory and give you some speedups at the cost of sometimes slightly reduced quality.

Optimize for low VRAM

Enabling this will make sure only the ai model parts which are needed for computation are kept on the GPU. This might lower VRAM usage under some settings at the cost of moving ai models in and out of GPU memory.

Samples (not available for all settings)

The number of ai samples to calculate. This will improve the models accuracy.

Parallel (only available if Samples > 2)

This will render all samples at the same time (faster), if disabled computation might be slower but require less VRAM.

Computation Tiles (not available for all settings)

Split the computation into several tiles. This can help if you run out of memory.