vufinder/vggt-1b-point 🖼️✓🔢 → ❓

▶️ 136 runs 📅 Oct 2025 ⚙️ Cog 0.16.8 🔗 GitHub 📄 Paper ⚖️ License
3d-reconstruction camera-pose-estimation depth-estimation image-to-3d point-cloud-generation video-to-3d

About

Feed-forward neural network that directly infers all key 3D attributes of a scene.

Example Output

Output

{"data":["https://replicate.delivery/czjl/rXIj8Uzn90JVNdkz3yDLQiMiW56ff4ZDyRpMcEf0aVLqDoeVB/image_0001.json"],"point_cloud":"https://replicate.delivery/czjl/smAXWeS4SXxmZidAYvG2VOxlHrC6wh4bJjESDpPaCUk6AqvKA/point_cloud.glb"}

Performance Metrics

4.59s Prediction Time
375.54s Total Time
All Input Parameters 
{
  "images": [
    "https://replicate.delivery/pbxt/NqKXWQsMgETBJsNUFgV06K8bhdjyeu1zCOtkl9j2qdw0lOdT/outdoor_001.jpg"
  ],
  "return_pcd": true
}
Input Parameters
inputs (required) Type: array
Input files, accepts JPG, JPEG, PNG, WEBP files for images and MP4, AVI, MOV files for video. The input images and sampled video frames will be padded to a single aspect ratio and resized to a maximum dimension of 518 pixels.
return_pcd Type: booleanDefault: true
Whether to return a point cloud file or not.
sampling_rate Type: integerDefault: 24
Sampling rate for video input as every n-th frame. Only applies to video inputs. First and last frames of the video will always be included.
Output Schema
Example Execution Logs 
Received 1 valid images.
Running inference...
Inference done!
Postprocessing the results...
Building GLB scene...
GLB Scene built!
Dumping data to 1 JSON files...
Dumped 1 JSON files!
Postprocessed the results!
Version Details
Version ID
ce6720fe4893da4112123529c1c065211bd2ed906c2631de03c2a794f86543fc
Version Created
October 17, 2025
Run on Replicate →