Weiqi Zhang, Wenyuan Zhang, Yu-Shen Liu, Junsheng Zhou · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.28631 · cited by 0 works (OpenAlex) · open-access PDF
구체적인 세계 시뮬레이션을위한 현재 세계 모델은 일반적으로 두 개의 구별 된 경로를 따릅니다 : (1) 비디오 생성 모델 (예를 들어, Sora), 현실적인 외관을 시뮬레이션하지만 3D 일관성을 보존하지 못하는; 및 (2) 3D 생성 모델 (예를 들어, 마블), 벤메트적으로 일관성있는 장면을 생성하지만 종종 렌더링 할 수있는 4D 그래픽 원시를 생성하는 동안 정적, 현실적인 관찰을 제공합니다. 우리는 비디오 기반과 3D 기반의 세계 모델을 연결하고 두 가지의 이점을 결합하는 통합 된 프레임 워크 AEON을 제시합니다. AEON의 핵심 통찰력은 텍스트 또는 이미지 조건화 된 비디오 중에서 작동하는 생성 모델에 있습니다. - 특히 4D
Machine translation (Meta M2M100); the English original follows.
Current world models for explicit world simulation typically follow two distinct pathways: (1) video generative models (e.g., Sora), which simulate realistic appearances but fail to preserve 3D consistency; and (2) 3D generative models (e.g., Marble), which generate geometrically consistent scenes but often yield static, less realistic observations. We present AEON, a unified framework that bridges video-based and 3D-based world models and combines the benefits of both. The key insight of AEON lies in a generative model that operates within the text- or image-conditioned video latent space while producing renderable 4D graphics primitives---specifically, 4D Gaussian Splatting (4DGS)---as the explicit world representation. We train a 4D reconstruction model to predict both 4DGS and camera poses from monocular videos, serving as our initialized 4D decoder. Furthermore, we design a domain adapter that translates generative video latents into reconstructive 4D latents through a distillation process on the video VAE. AEON naturally supports video-based world modeling by rendering 4DGS at predicted camera trajectories, and constructs a persistent 4D environment with scene dynamics for realistic world simulation. Consequently, AEON empowers a diverse range of world modeling applications and achieves state-of-the-art performance on standard benchmarks. Project Page: https://weiqi-zhang.github.io/AEON
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Computer science, Generative grammar, Rendering (computer graphics), Artificial intelligence, Generative model, Computer graphics
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28631, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange