| license: apache-2.0 | |
| pipeline_tag: image-to-3d | |
| # 3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Image | |
| [**Project Page**](https://zx-yin.github.io/3dfixer/) | [**Paper**](https://huggingface.co/papers/2604.04406) | [**GitHub**](https://github.com/HorizonRobotics/3D-Fixer) | |
| 3D-Fixer introduces a novel **In-Place Completion** paradigm to create high-fidelity 3D scenes from a single image. It extends 3D object generative priors to generate complete 3D assets conditioned on partially visible point clouds, using fragmented geometry as a spatial anchor to preserve layout fidelity without the need for time-consuming pose optimization. | |
| ## Sample Usage | |
| The model can be loaded using the following code snippet from the [official repository](https://github.com/HorizonRobotics/3D-Fixer): | |
| ```python | |
| # Load the pretrained model | |
| ThreeDFixerPipeline.from_pretrained("HorizonRobotics/3D-Fixer") | |
| ``` | |
| ## Dataset | |
| The model was trained on **ARSG-110K**, a large-scale scene-level dataset comprising over 110K diverse scenes and 3M annotated images with high-fidelity 3D ground truth. | |
| ## Citation | |
| ```bibtex | |
| @inproceedings{yin2026tdfixer, | |
| title={3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Image}, | |
| author={Yin, Ze-Xin and Liu, Liu and Wang, Xinjie and Sui, Wei and Su, Zhizhong and Yang, Jian and Xie, jin}, | |
| booktitle={Proceedings of the Computer Vision and Pattern Recognition Conference}, | |
| year={2026} | |
| } | |
| ``` |