| title | Walking in the Implicit: Interactive World Exploration via Neural Scene Representation |
|---|---|
| authors | Zhiqi Li, Chengrui Dong, Zhenhua Du, Hangning Zhou, Cong Qiu, Hailong Qin, Mu Yang, Dongxu Wei, Peidong Liu |
| date | 2026-06-29 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.30045 |
| upvotes | 5 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Interactive video generation systems for camera-controlled world exploration roll out growing sequences of latent video frames, entangling state transition with high-frequency observation synthesis. We propose Walking in the Implicit, a scene-centric paradigm that changes the rollout variable from frame latents to a fixed-length, renderable implicit state, termed Neural Implicit Scene (NIS). This factorizes interactive generation into stochastic transition of a compact scene state and deterministic pose-conditioned rendering given the sampled state. We instantiate this paradigm as NeuWorld: a transformer VAE learns locally anchored NIS from sparse posed frames, and a diffusion transformer evolves NIS conditioned on future camera trajectories and geometry-aware retrieved history. By reusing the VAE encoder as a unified conditioner, NeuWorld maps camera, reference-image, and history cues into the same NIS modality, avoiding external heterogeneous encoders. Trained from scratch on public posed-view data without pretrained video backbones or auxiliary 3D reconstructors, NeuWorld achieves strong long-horizon consistency with favorable inference efficiency. |
cite
@misc{li2026walking,
title={Walking in the Implicit: Interactive World Exploration via Neural Scene Representation},
author={Zhiqi Li and Chengrui Dong and Zhenhua Du and Hangning Zhou and Cong Qiu and Hailong Qin and Mu Yang and Dongxu Wei and Peidong Liu},
year={2026},
eprint={2606.30045},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.30045}
}