kfarr/tencent-hy-world-2.0
Tencent WorldMirror 2.0: feed-forward 3D reconstruction from multi-view images or video
Run kfarr/tencent-hy-world-2.0 with an API
Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.
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 |
|---|---|---|---|
| input_file |
string
|
A video file (mp4/mov/etc.) or a .zip archive of multi-view images. With a video, frames are extracted at the given fps.
|
|
| target_size |
integer
|
952
Min: 224 Max: 1568 |
Maximum resolution (longest edge). Images are resized and center-cropped to the nearest multiple of 14.
|
| fps |
integer
|
1
Min: 1 Max: 30 |
Frames-per-second to extract from a video input.
|
| video_max_frames |
integer
|
32
Min: 2 Max: 128 |
Maximum number of frames to use from a video input.
|
| save_gaussians |
boolean
|
True
|
Save 3D Gaussian splats (gaussians.ply).
|
| save_points |
boolean
|
True
|
Save dense point cloud (points.ply).
|
| save_depth |
boolean
|
True
|
Save per-view depth maps (PNG previews + .npy).
|
| save_normal |
boolean
|
True
|
Save per-view surface-normal maps.
|
| save_camera |
boolean
|
True
|
Save predicted camera parameters (camera_params.json).
|
| apply_sky_mask |
boolean
|
True
|
Mask out the sky region before reconstruction.
|
| apply_edge_mask |
boolean
|
True
|
Mask out unreliable depth/normal discontinuities.
|
| compress_gs_max_points |
integer
|
5000000
Min: 100000 Max: 20000000 |
Max number of gaussians to retain in the output PLY.
|
| compress_pts_max_points |
integer
|
2000000
Min: 100000 Max: 10000000 |
Max number of points to retain in points.ply.
|
{
"type": "object",
"title": "Input",
"required": [
"input_file"
],
"properties": {
"fps": {
"type": "integer",
"title": "Fps",
"default": 1,
"maximum": 30,
"minimum": 1,
"x-order": 2,
"description": "Frames-per-second to extract from a video input."
},
"input_file": {
"type": "string",
"title": "Input File",
"format": "uri",
"x-order": 0,
"description": "A video file (mp4/mov/etc.) or a .zip archive of multi-view images. With a video, frames are extracted at the given fps."
},
"save_depth": {
"type": "boolean",
"title": "Save Depth",
"default": true,
"x-order": 6,
"description": "Save per-view depth maps (PNG previews + .npy)."
},
"save_camera": {
"type": "boolean",
"title": "Save Camera",
"default": true,
"x-order": 8,
"description": "Save predicted camera parameters (camera_params.json)."
},
"save_normal": {
"type": "boolean",
"title": "Save Normal",
"default": true,
"x-order": 7,
"description": "Save per-view surface-normal maps."
},
"save_points": {
"type": "boolean",
"title": "Save Points",
"default": true,
"x-order": 5,
"description": "Save dense point cloud (points.ply)."
},
"target_size": {
"type": "integer",
"title": "Target Size",
"default": 952,
"maximum": 1568,
"minimum": 224,
"x-order": 1,
"description": "Maximum resolution (longest edge). Images are resized and center-cropped to the nearest multiple of 14."
},
"apply_sky_mask": {
"type": "boolean",
"title": "Apply Sky Mask",
"default": true,
"x-order": 9,
"description": "Mask out the sky region before reconstruction."
},
"save_gaussians": {
"type": "boolean",
"title": "Save Gaussians",
"default": true,
"x-order": 4,
"description": "Save 3D Gaussian splats (gaussians.ply)."
},
"apply_edge_mask": {
"type": "boolean",
"title": "Apply Edge Mask",
"default": true,
"x-order": 10,
"description": "Mask out unreliable depth/normal discontinuities."
},
"video_max_frames": {
"type": "integer",
"title": "Video Max Frames",
"default": 32,
"maximum": 128,
"minimum": 2,
"x-order": 3,
"description": "Maximum number of frames to use from a video input."
},
"compress_gs_max_points": {
"type": "integer",
"title": "Compress Gs Max Points",
"default": 5000000,
"maximum": 20000000,
"minimum": 100000,
"x-order": 11,
"description": "Max number of gaussians to retain in the output PLY."
},
"compress_pts_max_points": {
"type": "integer",
"title": "Compress Pts Max Points",
"default": 2000000,
"maximum": 10000000,
"minimum": 100000,
"x-order": 12,
"description": "Max number of points to retain in points.ply."
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
{
"type": "string",
"title": "Output",
"format": "uri"
}