--- license: cc-by-nc-4.0 pipeline_tag: image-to-3d --- # GS-ROR2: Bidirectional-guided 3DGS and SDF for Reflective Object Relighting and Reconstruction This repository contains the official checkpoints and results for **GS-ROR2**, a novel method presented in the paper [GS-ROR2: Bidirectional-guided 3DGS and SDF for Reflective Object Relighting and Reconstruction](https://arxiv.org/abs/2406.18544). This work will be presented at ACM TOG 2025. GS-ROR2 significantly advances 3D Gaussian splatting (3DGS) for inverse rendering, enabling the creation of high-quality relightable 3D assets.

## Links - 📄 **Paper**: [GS-ROR2: Bidirectional-guided 3DGS and SDF for Reflective Object Relighting and Reconstruction](https://arxiv.org/abs/2406.18544) - 🌐 **Project Page**: [https://nk-cs-zzl.github.io/projects/dsdf/index.html](https://nk-cs-zzl.github.io/projects/gsror/index.html) - 💻 **GitHub Repository**: [https://github.com/NK-CS-ZZL/DiscretizedSDF](https://github.com/NK-CS-ZZL/GS-ROR) ## Usage For detailed installation instructions, environment setup, and information on training and evaluation, please refer to the [official GitHub repository](https://github.com/NK-CS-ZZL/GS-ROR). To run a quick relighting video demo with the provided checkpoints: 1. Clone the repository: ```bash git clone https://github.com/NK-CS-ZZL/GS-ROR.git cd GS-ROR ``` 2. Follow the installation steps on the [GitHub repository's "Dependencies and Installation" section](https://github.com/NK-CS-ZZL/GS-ROR#dependencies-and-installation) to set up the environment and dependencies. 3. Download pretrained models (e.g., from [HuggingFace](https://huggingface.co/lalala125/GSROR) as mentioned in the GitHub README) and place them in the `pretrained` folder. 4. Run the demo script: ```bash sh demo.sh ``` ## Citation If you find our work useful for your research, please consider citing our paper: ```bibtex @inproceedings{zhu_2025_gsror, title={GS-ROR^2: Bidirectional-guided 3DGS and SDF for Reflective Object Relighting and Reconstruction}, author={Zhu, Zuo-Liang and Yang, Jian and Wang, Beibei}, journal = {ACM Transactions on Graphics (TOG)}, year={2025}, publisher = {ACM}, doi={10.1145/3759248}, } ```