paper-with-me

홈 › Papers

WorldReel: 4D Video Generation with Consistent Geometry and Motion Modeling

2025-12-08 · Shaoheng Fang, Hanwen Jiang, Yunpeng Bai, Niloy J. Mitra, Qixing Huang arxiv

Recent video generators achieve striking photorealism, yet remain fundamentally inconsistent in 3D. We present WorldReel, a 4D video generator that is natively spatio-temporally consistent. WorldReel jointly produces RGB frames together with 4D scene representations, including pointmaps, camera trajectory, and dense flow mapping, enabling coherent geometry and appearance modeling over time. Our explicit 4D representation enforces a single underlying scene that persists across viewpoints and dynamic content, yielding videos that remain consistent even under large non-rigid motion and significant camera movement. We train WorldReel by carefully combining synthetic and real data: synthetic data providing precise 4D supervision (geometry, motion, and camera), while real videos contribute visual diversity and realism. This blend allows WorldReel to generalize to in-the-wild footage while preserving strong geometric fidelity. Extensive experiments demonstrate that WorldReel sets a new state-of-the-art for consistent video generation with dynamic scenes and moving cameras, improving metrics of geometric consistency, motion coherence, and reducing view-time artifacts over competing methods. We believe that WorldReel brings video generation closer to 4D-consistent world modeling, where agents can render, interact, and reason about scenes through a single and stable spatiotemporal representation.

📄 PDF Abstract BibTeX arXiv:2512.07821

Code (0)

등록된 구현이 없습니다.

Tasks

Video Generation

Similar Papers 제목 키워드 기반

Alignment Is All You Need For X-to-4D Generation

2026-07-02 · Qiaowei Miao, Kehan Li, Yawei Luo, Yi Yang arxiv

Generative diffusion models excel at synthesizing high-quality images, videos, and 3D content under multimodal control. However, arbitrary user-defined modality-to-4D (X-to-4D) generation remains challenging due to the h…

From Single Images to Motion Policies via Video-Generation Environment Representations

2025-05-25 · Weiming Zhi, Ziyong Ma, Tianyi Zhang, Matthew Johnson-Roberson

Autonomous robots typically need to construct representations of their surroundings and adapt their motions to the geometry of their environment. Here, we tackle the problem of constructing a policy model for collision-f…

Depth EstimationMonocular Depth EstimationMotion GenerationVideo Generation

PanoWorld: Geometry-Consistent Panoramic Video World Modeling

2026-05-14 · Le Jiang, Xiangyu Bai, Bishoy Galoaa, Shayda Moezzi 외 arxiv

We present PanoWorld, a panoramic video world model that generates geometry-consistent 360$\degree$ video from a single image and a caption. Existing panoramic video methods optimize primarily for visual realism and do n…

Video Generation

OrthoPhys: Physically Plausible Video Generation with Orthogonal-View Geometry Guidance

2026-03-19 · Cong Wang, Hanxin Zhu, Xiao Tang, Jiayi Luo 외 arxiv

Recent progress in video generation has led to substantial improvements in visual fidelity, yet ensuring physically consistent motion remains a fundamental challenge. Intuitively, this limitation can be attributed to the…

Video Generation

PV3D: A 3D Generative Model for Portrait Video Generation

2022-12-13 · Zhongcong Xu, Jianfeng Zhang, Jun Hao Liew, Wenqing Zhang 외

Recent advances in generative adversarial networks (GANs) have demonstrated the capabilities of generating stunning photo-realistic portrait images. While some prior works have applied such image GANs to unconditional 2D…

Video Generation