Mean blur on the GPU compute backend (wgpu/Metal/Vulkan), bit-aligned with the CPU reference. An order of magnitude faster for bulk processing; parameters match opencv_blur_filter.

Module：GPU image processing · Task type：gpu_box_blur

Ports

Inputs

PortTypeRequired
inImage / cv::Mat✓

Outputs

PortTypeRequired
outtask_graph::Image✓

Parameters

参数类型默认值范围 / 选项说明
kernel_sizeint5[1, 99] (step 2)kernel edge length in pixels; must be a positive odd number

Example graph

A minimal runnable pipeline (read → process → write). Drag it into GraphStudio or open via --open; replace data/test.png with a real path.

{
  "version": "2.0",
  "tasks": [
    {
      "id": "read",
      "type": "opencv_image_read",
      "params": {
        "file_path": "data/test.png"
      }
    },
    {
      "id": "node",
      "type": "gpu_box_blur",
      "params": {
        "kernel_size": 5
      }
    },
    {
      "id": "save",
      "type": "opencv_image_write",
      "params": {
        "file_path": "out_out.png"
      }
    }
  ],
  "edges": [
    {
      "from": "read",
      "from_port": "out",
      "to": "node",
      "to_port": "in"
    },
    {
      "from": "node",
      "from_port": "out",
      "to": "save",
      "to_port": "in"
    }
  ]
}

Notes

  • Fails the task when the GPU backend can’t init (no silent CPU fallback; use blend’s device=auto when you need fallback semantics).

Part of the GraphStudio node guide series; parameters reflect the latest release.