| | --- |
| | license: cc-by-4.0 |
| | --- |
| | |
| | # **Amodal3R**: Amodal 3D Reconstruction from Occluded 2D Images |
| |
|
| | Given partially visible objects within images, Amodal3R reconstructs semantically meaningful 3D assets with reasonable geometry and plausible appearance. |
| |
|
| | Arxiv: https://arxiv.org/abs/2503.13439 |
| |
|
| | Project Page: https://sm0kywu.github.io/Amodal3R/ |
| |
|
| | Our model is built upon the "foundation" model [TRELLIS](https://trellis3d.github.io/). The pre-trained model weights are fetched from https://huggingface.co/JeffreyXiang/TRELLIS-image-large. Thanks to their impressive work!!! |
| |
|
