Input
ExecutionInitiate Execution
AI/ML/ONNX/Vision
Estimate depth from a single image using ONNX models. Download models from: MiDaS (https://github.com/isl-org/MiDaS/releases), DPT (https://huggingface.co/Intel/dpt-large/tree/main), Depth Anything (https://huggingface.co/depth-anything/Depth-Anything-V2-Small/tree/main)
Scores range from 0 to 10. Higher values mean more impact, exposure, or operational weight.
Initiate Execution
ONNX Depth Model Session
Cache ID for Session
Input Image
Model provider type
MiDaS models (small, base, large)
DPT (Dense Prediction Transformer) models
Depth Anything models
Generic depth model (single input, single output)
Model input size (default 384 for MiDaS)
Done
Estimated depth map
Depth values normalized to 0-1 range (closer = lower values)
Width of the depth map
Height of the depth map
Minimum depth value (before normalization)
Maximum depth value (before normalization)
Grayscale depth visualization