# S2Tok: Streaming 3D Gaussian Reconstruction with Persistent Spatial Tokens

arXiv: https://arxiv.org/abs/2610.08978 · HTML: https://mlsanity.com/paper/2610.08978/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 35 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Builds on (most cited first, 9 of 9)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Depth Anything 3: Recovering the Visual Space from Any Views](https://mlsanity.com/paper/2511.10647/) (2025)
- [Stereo Magnification: Learning View Synthesis using Multiplane Images](https://mlsanity.com/paper/1805.09817/) (2018)
- [TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens](https://mlsanity.com/paper/2604.15239/) (2026)
- [S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton of Articulated Objects from Single Monocular Video](https://mlsanity.com/paper/2405.12607/) (2024)
- [GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens](https://mlsanity.com/paper/2604.15284/) (2026)
- [ZipSplat: Fewer Gaussians, Better Splats](https://mlsanity.com/paper/2606.05102/) (2026)
- [Self-Calibrating 4D Novel View Synthesis from Monocular Videos Using Gaussian Splatting](https://mlsanity.com/paper/2406.01042/) (2024)
- [Helix4D: Complex 4D Mesh Generation](https://mlsanity.com/paper/2605.26109/) (2026)

## Abstract (arXiv)

Streaming 3D reconstruction requires more than a sequence of geometric predictions: it requires a persistent scene state that can incorporate new evidence and remain renderable as observations arrive. Latent spatial tokens offer a promising representation for this purpose, but constructing them from an image collection leaves open how to maintain them online, where each observation may both revisit known regions and reveal new content. We introduce S2Tok, a feed-forward framework that maintains a size-adaptive, persistent scene state from uncalibrated image streams. Its central idea is to distinguish updates to the existing representation from selective expansion. A spatially informed transformer integrates each incoming observation with the persistent scene tokens, while a learned admission module selectively expands the representation to limit redundant storage. A hierarchical decoder and Gaussian head convert the evolving state into non-pixel-aligned 3D Gaussians, enabling novel-view rendering without caching previous frames. Experiments across four benchmarks demonstrate competitive streaming rendering quality with compact Gaussian representations. These results support latent spatial tokens as a persistent computational state for online 3D reconstruction, combining learned scene updates with explicit Gaussian rendering.