---
library_name: pytorch
tags:
  - 3d-gaussian-splatting
  - novel-view-synthesis
  - feed-forward
  - rlsplat
---

# RLSplat

This model repository contains the inference-only RLSplat checkpoint in Safetensors format.
Try it in the [interactive Hugging Face demo](https://huggingface.co/spaces/Knowing/RLSplat-demo) with 2–4 images of the same scene.
Training code will be released in a future update.

| Checkpoint | Training data | Training context views | Folder |
| --- | --- | ---: | --- |
| RLSplat | RE10K | dynamic 2–24 (maximum 24) | `re10k-24view` |

The checkpoint was exported from the submitted 5,000-step RE10K Lightning checkpoint. Optimizer state, training metadata, and training-only tensors are not included.

Use the model with the [RLSplat evaluation code](https://github.com/K-nowing/RLSplat/tree/release/evaluation-only-iclr26):

```bash
python -m src.main '+evaluation=re10k' \
  checkpointing.load=hf://Knowing/RLSplat/re10k-24view/model.safetensors \
  'dataset.re10k.roots=[/path/to/re10k]' \
  dataset.re10k.view_sampler.index_path=assets/evaluation_index_re10k.json
```

See the repository README for installation, data preparation, other context-view selections, and full budget-sweep examples.