Skip to main content
This node renders a visualization from Depth Anything 3 geometry data. It can output depth maps, confidence maps, or sky masks depending on the selected output mode.

Inputs

ParameterDescriptionData TypeRequiredRange
da3_geometryThe Depth Anything 3 geometry data packet containing depth, and optionally sky and confidence tensorsDA3_GEOMETRYYes-
outputThe type of visualization to render. Options include depth, depth_colored, sky_mask, and confidence. Each option has its own set of sub-parameters.COMBOYes"depth"
"depth_colored"
"sky_mask"
"confidence"

Sub-parameters for output options

When output is set to "depth" or "depth_colored":
ParameterDescriptionData TypeRequiredRange
normalizationThe depth normalization method. v2_style uses mean/std normalization for perceptually balanced results (default). min_max stretches the full depth range to [0, 1] for maximum contrast. raw preserves metric units for Metric model without scaling.COMBOYes"v2_style"
"min_max"
"raw"
apply_sky_clipClip sky-region depth to the 99th percentile of foreground depth before normalization. Requires a sky key in the da3_geometry input (for Mono/Metric models only). Default: FalseBOOLEANYesTrue
False
When output is set to "sky_mask":
ParameterDescriptionData TypeRequiredRange
coloredApply the Turbo colormap to the sky mask. Default: FalseBOOLEANYesTrue
False
When output is set to "confidence":
ParameterDescriptionData TypeRequiredRange
coloredApply the Turbo colormap to the confidence map. Default: FalseBOOLEANYesTrue
False

Parameter Constraints

  • When apply_sky_clip is set to True, the da3_geometry input must contain a sky tensor. This is only available when using Mono or Metric models. If the sky tensor is missing, the node will raise an error.
  • The sky_mask output option requires a sky tensor in the da3_geometry input. This is only available with Mono or Metric models.
  • The confidence output option requires a confidence tensor in the da3_geometry input. This is only available with Small or Base models.

Outputs

Output NameDescriptionData Type
IMAGEThe rendered visualization as an image tensor. For depth outputs, returns a greyscale or colored depth map. For sky_mask and confidence, returns either a greyscale or colored visualization depending on the colored parameter.IMAGE
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): 54d4cde95a916cac26c8a2e19c5623e794d46c0d7652f1c8204f9f2a0deabe0c