Nodes/camera-comfyUI/MotionMaskFromDepth
ComfyUI Node

MotionMaskFromDepth

Detects dynamic pixels from a depth+pose sequence (1.0 = moving).

By Alexankharin·Created about a year ago·Updated 22 days ago· 35
MotionMaskFromDepth
  • depth_seq
  • trajectory
  • motion_mask
input_projection
input_horizontal_fov90.00
threshold0.10
frame_gap4
dilate2
deviceauto
CategoryCamera/GSplat4D

Inputs (8)

NameTypeDefaultDescription
depth_seqTENSORDepth sequence [T,H,W] (radial distance).
trajectoryTENSORWorld-to-camera poses [T,4,4] (or [K,4,4]; interpolated to T).
input_projectionCOMBO3 options: PINHOLE, FISHEYE, EQUIRECTANGULAR
input_horizontal_fovFLOAT90.001–360
thresholdFLOAT0.100–10Relative depth residual |d_proj - d_sampled|/d_sampled above which a pixel is dynamic.
frame_gapINT41–256Temporal gap for forward/backward reprojection checks.
dilateINT20–64Dilation radius (pixels) of the dynamic mask.
deviceoptCOMBOauto3 options: auto, cpu, cuda

Outputs (1)

NameTypeDescription
motion_maskMASK