I-Scene: 3D Instance Models are Implicit Generalizable Spatial Learners

🌟 CVPR 2026

🏠 Project Page | 📄 Paper | 🤗 Model | 📦 Dataset | 🎮 Online Demo

Lu Ling¹, Yunhao Ge², Yichen Sheng², Aniket Bera¹

¹Purdue University    ²NVIDIA Research

🌟 Overview

I-Scene reprograms a pre-trained 3D instance generator to act as a scene-level learner, replacing dataset-bounded supervision with model-centric spatial supervision. This unlocks the generator's transferable spatial knowledge, enabling generalization to unseen layouts and novel object compositions.

🔑 Key Features

• Model Flexibility: A pre-trained 3D instance generator can be directly reprogrammed as a scene-level spatial learner, without scene-level annotations.
• Transferable Spatial Prior: The reprogrammed model's spatial prior provides a rich learning signal for inferring proximity, support, and symmetry from purely geometric cues.
• Data Independence: The model learns spatial knowledge on non-semantic scenes from randomly composed objects, removing dependency on annotated data.
• Strong Generalizability: It allows for easy generalization to unseen layouts and various spatial relations in a feed-forward manner without per-scene optimization.

🔥 Updates

• Release inference code and sparse structure flow transformer
• Release interactive huggingface demo and usage
• Release training data scripts
• Release evaluation code

🚀 Demo

Visit our Project Page for:

• Interactive 3D scene visualization
• Comparison with state-of-the-art methods
• More visualization examples

📦 Installation

# Coming soon
git clone https://github.com/LuLing06/I-Scene-project.git
cd I-Scene-project

🎯 Usage

📜 Citation

If you find this work helpful, please consider citing our paper:

@article{ling2025iscene,
  title={I-Scene: 3D Instance Models are Implicit Generalizable Spatial Learners},
  author={Ling, Lu and Ge, Yunhao and Sheng, Yichen and Bera, Aniket},
  journal={arXiv preprint arXiv:2512.13683},
  year={2025}
}

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

We thank the authors of TRELLIS, and other related works for their inspiring research.

The website template is borrowed from Nerfies and MIDI.