NeoVerse：利用野外單目影片增強四維世界模型

NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos

January 1, 2026

作者: Yuxue Yang, Lue Fan, Ziqi Shi, Junran Peng, Feng Wang, Zhaoxiang Zhang

cs.AI

摘要

本文提出NeoVerse——一個多功能的4維世界模型，能實現4維重建、新軌跡影片生成及豐富的下游應用。我們首先指出當前4維世界建模方法普遍存在的可擴展性局限，其根源在於依賴昂貴且專業的多視角4維數據，或繁瑣的訓練預處理流程。與之相對，NeoVerse的核心設計理念在於使完整流程能靈活適應各類真實世界單目影片。具體而言，NeoVerse具備無需姿態估計的前饋式4維重建、在線單目退化模式模擬等高度協同的技術方案。這些設計使NeoVerse在跨領域應用中展現出卓越的通用性與泛化能力。同時，NeoVerse在標準重建與生成基準測試中達到了最先進的性能。項目頁面請訪問：https://neoverse-4d.github.io

English

In this paper, we propose NeoVerse, a versatile 4D world model that is capable of 4D reconstruction, novel-trajectory video generation, and rich downstream applications. We first identify a common limitation of scalability in current 4D world modeling methods, caused either by expensive and specialized multi-view 4D data or by cumbersome training pre-processing. In contrast, our NeoVerse is built upon a core philosophy that makes the full pipeline scalable to diverse in-the-wild monocular videos. Specifically, NeoVerse features pose-free feed-forward 4D reconstruction, online monocular degradation pattern simulation, and other well-aligned techniques. These designs empower NeoVerse with versatility and generalization to various domains. Meanwhile, NeoVerse achieves state-of-the-art performance in standard reconstruction and generation benchmarks. Our project page is available at https://neoverse-4d.github.io