You're looking at a specific version of this model. Jump to the model overview.

kfarr /vid2scene:4846c855

Input schema

The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.

Field Type Default value Description
video
string
Source video (a slow, steady orbit around a static " "subject works best).
reconstruction_method
None
glomap
Structure-from-Motion method. glomap (default) needs no " "model weights.
target_framecount
integer
600

Min: 30

Max: 2000

Target number of frames to sample from the video.
training_num_steps
integer
30000

Min: 2000

Max: 30000

gsplat training steps. Fewer is faster but lower quality.
training_max_num_gaussians
integer
500000

Min: 100000

Max: 600000

Cap on the number of Gaussians. This is the primary " "control on output .ply size: the gsplat exporter writes 164 bytes " "per Gaussian (position + SH degree-2 color + opacity/scale/rot), so " "~640k Gaussians ~= 100 MB. The ceiling here (600k ~= 98 MB) keeps " "every output under 3DStreet's 100 MB save limit; the default 500k " "(~82 MB) leaves headroom.
equirectangular
boolean
False
Treat the input as 360/equirectangular video.
use_background_sphere
boolean
False
Add a background sphere for distant/sky content. Helps " "outdoor or 360 captures where the background is far away.
remove_background
boolean
False
Remove the background from each frame before " "reconstruction (InSPyReNet). Good for isolating a single object; " "leave OFF for scenes/environments where you want the surroundings.
apriltag_size_meters
number

Min: 0.01

Max: 10

If an AprilTag of known physical size (in meters) is " "visible in the video, set it here to scale the reconstruction to " "real-world units. Leave unset to skip metric scaling.

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}