ComfyUI Node
cv2.optflow.calcOpticalFlowSparseToDense
Raw wrapper of cv2.optflow.calcOpticalFlowSparseToDense(from_, to, grid_step?, k?, sigma?, use_post_proc?, fgs_lambda?, fgs_sigma?). Parameters marked '?' are optional; blank means OpenCV default. From the opencv-contrib 'optflow' module. See the OpenCV documentation for details.
cv2.optflow.calcOpticalFlowSparseToDense
- from_
- to
- nparray
◄grid_step8►
◄k128►
◄sigma0.0500►
◄use_post_proctrue►
◄fgs_lambda500.0000►
◄fgs_sigma1.5000►
Categoryimage/CV/low-level/optflow
Inputs (8)
| Name | Type | Default | Description |
|---|---|---|---|
| from_ | NPARRAY,IMAGE,MASK | - - - Accepts a ComfyUI IMAGE/MASK directly (frame 0 of a batch) or an NPARRAY. Arithmetic ops (add, multiply, etc.) process the full IMAGE batch when both inputs have the same batch size. | |
| to | NPARRAY,IMAGE,MASK | second 8-bit 3-channel or 1-channel image of the same size as from Accepts a ComfyUI IMAGE/MASK directly (frame 0 of a batch) or an NPARRAY. Arithmetic ops (add, multiply, etc.) process the full IMAGE batch when both inputs have the same batch size. | |
| grid_stepopt | INT | 8-2147483648–2147483647 | stride used in sparse match computation. Lower values usually result in higher quality but slow down the algorithm. Preset to the OpenCV default (8). |
| kopt | INT | 128-2147483648–2147483647 | number of nearest-neighbor matches considered, when fitting a locally affine model. Lower values can make the algorithm noticeably faster at the cost of some quality degradation. Preset to the OpenCV default (128). |
| sigmaopt | FLOAT | 0.0500-1e+38–1e+38 | parameter defining how fast the weights decrease in the locally-weighted affine fitting. Higher values can help preserve fine details, lower values can help to get rid of the noise in the output flow. Preset to the OpenCV default (0.05). |
| use_post_procopt | BOOLEAN | true | defines whether the ximgproc::fastGlobalSmootherFilter() is used for post-processing after interpolation Preset to the OpenCV default (True). |
| fgs_lambdaopt | FLOAT | 500.0000-1e+38–1e+38 | see the respective parameter of the ximgproc::fastGlobalSmootherFilter() Preset to the OpenCV default (500.0). |
| fgs_sigmaopt | FLOAT | 1.5000-1e+38–1e+38 | see the respective parameter of the ximgproc::fastGlobalSmootherFilter() Preset to the OpenCV default (1.5). |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| nparray | NPARRAY | — |