| --- |
| license: cc-by-4.0 |
| tags: |
| - 3d-reconstruction |
| - gaussian-splatting |
| - learned-optimizer |
| - computer-vision |
| - view-synthesis |
| - pytorch |
| --- |
| |
| # 🫧 Learn2Splat: Learned Optimizer for 3D Gaussian Splatting |
|
|
| **Learn2Splat** is a meta-learned optimizer for **3D Gaussian Splatting (3DGS)** that replaces hand-designed optimizers (e.g., Adam/SGD) with a learned update rule. |
|
|
| It improves early convergence speed while remaining stable over long optimization horizons without requiring learning-rate schedules or time-step conditioning. |
|
|
| ------------------------------------------------------------------------ |
|
|
| ## 🌐 Links |
|
|
| - Project page: https://naamapearl.github.io/learn2splat/ |
| - Code: https://github.com/autonomousvision/learn2splat |
| - Hugging Face: https://huggingface.co/autonomousvision/learn2splat |
|
|
| ------------------------------------------------------------------------ |
|
|
| ## ⚙️ Overview |
|
|
| Learn2Splat learns to optimize Gaussian scene representations by directly predicting structured parameter updates. |
|
|
| Key properties: |
|
|
| - Learned optimizer for 3D Gaussian Splatting |
| - Faster early convergence compared to standard optimizers |
| - Stable long-horizon optimization without LR schedules |
| - Zero-shot generalization to unseen scenes and resolutions |
|
|
| The model is trained across many scenes and applied without fine-tuning at test time. |
|
|
| ------------------------------------------------------------------------ |
|
|
| ## 📦 Checkpoints |
|
|
| This repository includes pretrained weights for: |
|
|
| - Learn2SplatSparse: sparse-view reconstruction |
| - Learn2SplatDense: dense-view reconstruction |
|
|
| See [MODEL_ZOO.md](https://huggingface.co/autonomousvision/learn2splat/blob/main/MODEL_ZOO.md) for details. |
|
|
| ------------------------------------------------------------------------ |
|
|
| ## 📚 Citation |
|
|
| If you find this project useful, please consider citing: |
|
|
| ```bibtex |
| @article{pearl2026learn2splat, |
| title = {Learn2Splat: Extending the Horizon of Learned 3DGS Optimization}, |
| author = {Pearl, Naama and Esposito, Stefano and Xu, Haofei and Peleg, Amit and |
| Gschoßmann, Patricia and Porzi, Lorenzo and Kontschieder, Peter and |
| Pons-Moll, Gerard and Geiger, Andreas}, |
| journal = {arXiv preprint arXiv:2605.15760}, |
| year = {2026} |
| } |
| ``` |
