PulseAugur
中
实时 13:49:04

新方法“Walking in the Implicit”可实现交互式视频生成

作者 PulseAugur 编辑部 · [3 个来源] ·

研究人员推出了一种名为“Walking in the Implicit”的新型交互式视频生成方法，该方法将场景表示为紧凑的神经隐式状态。该方法以 NeuWorld 为实例，将过程分为几个不同的阶段：从稀疏数据中学习场景状态，然后根据相机轨迹渲染帧。NeuWorld 利用了 transformer VAE 和 diffusion transformer，在不依赖预训练视频模型或 3D 重建工具的情况下实现了长时一致性。 AI

影响 通过将场景状态转换与帧渲染分离，为交互式视频生成引入了新的范例。

排序理由 该集群描述了一篇关于视频生成新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

新方法“Walking in the Implicit”可实现交互式视频生成

报道来源 [3]

  1. Hugging Face Daily Papers TIER_1 English(EN) ·

    Walking in the Implicit: Interactive World Exploration via Neural Scene Representation

    NeuWorld enables efficient interactive video generation by representing scenes as compact neural implicit states and using a transformer VAE with diffusion transformer for trajectory-conditioned rendering.

  2. arXiv cs.CV TIER_1 English(EN) · Zhiqi Li, Chengrui Dong, Zhenhua Du, Hangning Zhou, Cong Qiu, Hailong Qin, Mu Yang, Dongxu Wei, Peidong Liu ·

    Walking in the Implicit: Interactive World Exploration via Neural Scene Representation

    arXiv:2606.30045v1 Announce Type: new 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 Implici…

  3. arXiv cs.CV TIER_1 English(EN) · Peidong Liu ·

    Walking in the Implicit: Interactive World Exploration via Neural Scene Representation

    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 rol…

相关实体

相关话题