KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

#dsh #dsh-plugin #ai-agents #developer-tools #typescript #codex #cli #claude-code #mcp #rust #deepseek-harness #ai-agent

NeuWorld

★ 49 Open GitHub ↗

[ECCV 2026] Walking in the Implicit: Interactive World Exploration via Neural Scene Representation

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

<h1 align="center">Walking in the Implicit: Interactive World Exploration via Neural Scene Representation</h1>

Code will be released soon.

<a href="https://lizhiqi49.github.io">Zhiqi Li</a>1,2 &nbsp;
 <a href="https://github.com/forgetable233">Chengrui Dong</a>1,2 &nbsp;
 <a href="https://github.com/duzh11">Zhenhua Du</a>1,2 &nbsp;
 Hangning Zhou3,&dagger; &nbsp;
 Cong Qiu3 
 Hailong Qin3 &nbsp;
 Mu Yang3 &nbsp;
 <a href="https://wswdx.github.io">Dongxu Wei</a>2 &nbsp;
 <a href="https://ethliup.github.io">Peidong Liu</a>2,*

1Zhejiang University &nbsp;&nbsp;
 2Westlake University &nbsp;&nbsp;
 3Afari Intelligent Drive 
 &dagger;Project Lead &nbsp;&nbsp;
 *Corresponding Author

## News

- The public repository is under internal review. Code and checkpoints will be released soon.
- 🎉🎉 NeuWorld is accepted by ECCV 2026.

## Highlights

- **Scene-centric rollout.** We replace growing video-latent trajectories with a fixed-length, renderable Neural Implicit Scene (NIS) state.
- **Factorized interaction.** Each step decouples stochastic latent scene-state transition from deterministic pose-conditioned rendering.
- **Unified NIS conditioning.** Camera, reference-image, and retrieved history cues are mapped into the same NIS modality instead of separate heterogeneous encoders.
- **Long-horizon consistency.** NeuWorld is designed for camera-controlled exploration with revisitation consistency and favorable inference efficiency.
- **From-scratch training.** The model is trained on public posed-view datasets without pretrained video backbones or auxiliary 3D reconstructors.

## Method Overview

At each interaction step, the frozen NIS-VAE encoder maps the current observation and a sparse future pose trajectory to a partial NIS condition. Geometry-aware retrieval selects a history set and encodes it as memory NIS tokens. NIS-DiT samples the next local NIS state, and the frozen decoder renders future views under the queried poses.

## Citation

If you find our work useful, please cite:

```bibtex
@inproceedings{li2026neuworld,
  title     = {Walking in the Implicit: Interactive World Exploration via Neural Scene Representation},
  author    = {Li, Zhiqi and Dong, Chengrui and Du, Zhenhua and Zhou, Hangning and Qiu, Cong and Qin, Hailong and Yang, Mu and Wei, Dongxu and Liu, Peidong},
  booktitle = {European Conference on Computer Vision (ECCV)},
  year      = {2026}
}
```

NeuWorld

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README