3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection
🌟 GitHub Repository | 🚀 Project Page
Upload one image, camera parameters and language prompts to run the 3D object detection in the wild!
PLEASE NOTE: We are using ZeroGPU thanks to HuggingFace community Grant. However, while running on HuggingFace Space, it will take extra time to load the model for each inference. For faster visualization, please consider using a local machine to run our demo from our GitHub repository.
Examples
| Upload Image | Language Prompt | Score Threshold | fx | fy | cx | cy |
|---|