paper-with-me

홈 › Papers

DeepVerse: 4D Autoregressive Video Generation as a World Model

2025-06-01 · Junyi Chen, Haoyi Zhu, Xianglong He, Yifan Wang, Jianjun Zhou, Wenzheng Chang, Yang Zhou, Zizun Li, Zhoujie Fu, Jiangmiao Pang, Tong He

World models serve as essential building blocks toward Artificial General Intelligence (AGI), enabling intelligent agents to predict future states and plan actions by simulating complex physical interactions. However, existing interactive models primarily predict visual observations, thereby neglecting crucial hidden states like geometric structures and spatial coherence. This leads to rapid error accumulation and temporal inconsistency. To address these limitations, we introduce DeepVerse, a novel 4D interactive world model explicitly incorporating geometric predictions from previous timesteps into current predictions conditioned on actions. Experiments demonstrate that by incorporating explicit geometric constraints, DeepVerse captures richer spatio-temporal relationships and underlying physical dynamics. This capability significantly reduces drift and enhances temporal consistency, enabling the model to reliably generate extended future sequences and achieve substantial improvements in prediction accuracy, visual realism, and scene rationality. Furthermore, our method provides an effective solution for geometry-aware memory retrieval, effectively preserving long-term spatial consistency. We validate the effectiveness of DeepVerse across diverse scenarios, establishing its capacity for high-fidelity, long-horizon predictions grounded in geometry-aware dynamics.

📄 PDF Abstract BibTeX arXiv:2506.01103

Code (0)

등록된 구현이 없습니다.

Tasks

Video Generation

Similar Papers 제목 키워드 기반

Learning World Models for Interactive Video Generation

2025-05-28 · Taiye Chen, Xun Hu, Zihan Ding, Chi Jin

Foundational world models must be both interactive and preserve spatiotemporal coherence for effective future planning with action choices. However, present models for long video generation have limited inherent world mo…

In-Context LearningRetrievalRetrieval-augmented GenerationVideo Generation+1

Directing the World: Fast Autoregressive Video Generation with Compositional Human-Camera Control

2026-06-26 · Haoyuan Wang, Yabo Chen, Haibin Huang, Chi Zhang 외 arxiv

Building interactive world models requires generating realistic videos while maintaining controllable dynamics over long horizons. Autoregressive video generation offers a scalable foundation, but suffers from error accu…

Video Generation

Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models

2026-06-24 · Kaiwen Zheng, Guande He, Min Zhao, Jintao Zhang 외 arxiv

Autoregressive video diffusion with causal diffusion transformers has emerged as a major paradigm for real-time streaming video generation and action-conditioned interactive world models. In this work, we extend rCM, an …

Video Generation

DCARL: A Divide-and-Conquer Framework for Autoregressive Long-Trajectory Video Generation

2026-03-25 · Junyi Ouyang, Wenbin Teng, Gonglin Chen, Yajie Zhao 외 arxiv

Long-trajectory video generation is a crucial yet challenging task for world modeling primarily due to the limited scalability of existing video diffusion models (VDMs). Autoregressive models, while offering infinite rol…

Video Generation

Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing

2024-11-25 · Kaifeng Gao, Jiaxin Shi, Hanwang Zhang, Chunping Wang 외

With the advance of diffusion models, today's video generation has achieved impressive quality. To extend the generation length and facilitate real-world applications, a majority of video diffusion models (VDMs) generate…

DenoisingVideo Generation