🫧 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 for details.

---

📚 Citation

If you find this project useful, please consider citing:

@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}
}