Streaming autoregressive diffusion models enable real-time, long-horizon video generation, but their training objectives optimize local frame prediction rather than the geometry and dynamics of a coherent world: long rollouts accumulate geometric drift and degrade into static or unnatural motion. Recent bidirectional approaches address this problem using rewards signals built upon 3D Gaussian-Splatting reconstruction.
arXiv:2608. 19556v1 Announce Type: cross Abstract: Streaming autoregressive diffusion models enable real-time, long-horizon video generation, but their training objectives optimize local frame prediction rather than the geometry and dynamics of a coherent world: long rollouts accumulate geometric drift and degrade into static or unnatural motion.
By Yuanhao Ban, Jiaqi Feng, Hengguang Zhou, Xiaohuan Pei, Justin Cui, Cho-Jui Hsieh
The paper introduces 4DStreamCtrl, a system that unifies camera motion, object trajectories, and depth into a single 3D point‑track representation, enabling joint control, depth editing, and motion transfer in a single forward pass. By mining in‑the‑wild video for 3D motion supervision and encoding it with a lightweight Geometric Motion Head, the authors train a causal streaming student that can generate arbitrarily long videos in just four denoising steps, achieving 20 FPS on a single high‑end GPU for 480p video. This approach outperforms prior camera‑only, 2D, and offline‑3D methods in motion‑control precision while maintaining temporal coherence over hundreds of frames, thereby enabling interactive 4D‑controllable streaming generation for the first time.
By Shiqian Li, Chenguo Lin, Zhiguang Liu, Yu Tang, Jiarong Ou, Rui Chen, Yixin Zhu
Dream4D is a new framework for generating spatiotemporally coherent 4D content. It uses a two‑stage pipeline: first, few‑shot learning predicts optimal camera trajectories from a single image; second, a pose‑conditioned diffusion process creates geometrically consistent multi‑view sequences that are converted into a persistent 4D representation. The method uniquely combines rich temporal priors from video diffusion models with geometric awareness from reconstruction models, achieving higher quality metrics such as mPSNR and mSSIM compared to existing approaches.
By Xiaoyan Liu, Kangrui Li, Jiaxin Liu, Yuehao Song, Yujie Xing
arXiv:2607. 01202v1 Announce Type: cross Abstract: We present World from Motion, a method for generating freely renderable dynamic 3D Gaussian representations from monocular videos.
By Liyuan Zhu, Shengyu Huang, Amrita Mazumdar, Tianye Li, Zan Gojcic, Gordon Wetzstein, Iro Armeni, Shalini De Mello, Alex Trevithick
4D generation synthesizes dynamic 3D scenes from conditions such as text or images. Existing methods either reconstruct generated RGB videos with a separate 4D model or adapt a particular video generator to predict geometry directly.
arXiv:2607. 18367v1 Announce Type: new Abstract: Unlike conventional video game development, which relies on labor-intensive pipelines for asset production, animation, physics, and programming, video world models generate interactive environments from user inputs instantly.
By AlayaWorld Team, Kaipeng Zhang, Chuanhao Li, Yifan Zhan, Yongtao Ge, Yuanyang Yin, Jiaming Tan, Kang He, Liaoyuan Fan, Mingliang Zhai, Ruicong Liu, Xiaojie Xu, Xuangeng Chu, Zhen Li, Zhengyuan Lin, Zhixiang Wang, Zian Meng, Zihui Gao
Manifold4D introduces a new denoising strategy for video re‑shooting that injects a rendered point‑cloud directly into the initial noise manifold, eliminating the need for the render to be an explicit conditioning stream during denoising. This approach allows the network to rely solely on the source video as a visual condition, improving camera‑control accuracy on the DAVIS‑Traj benchmark and Vista4D set, with significant reductions in rotation and translation errors while maintaining video fidelity. User studies confirm enhanced trajectory following and dynamic consistency, especially for large yaw amplitudes and even when the render is corrupted.
By Yongqi Mao, Zijia Dai, Zhishuo Liu, Wei Xu, Kaiwei Wang, Guotao Meng
arXiv:2606. 28215v1 Announce Type: cross Abstract: Extracting dynamic 4D object interactions from massive, in-the-wild monocular videos offers a highly efficient data collection pathway for scaling Embodied AI and training VLAs.
By Jiaxin Li, Yuxiang Wu, Zhenkai Zhang, Xinrui Shi, Haoyuan Wang, Yichen Zhao, Su Linxiang, Chenyang Yu, Mingyu Zhang, Yifan Ding, Boran Wen, Li Zhang, Ruiyang Liu, Yong-Lu Li
Forge4D is a feed‑forward model that reconstructs temporally aligned 4D human representations from uncalibrated sparse‑view videos, enabling both novel view and novel time synthesis. It achieves this by jointly streaming 3D Gaussian reconstruction with dense motion prediction, using learnable state tokens for temporal consistency and a self‑supervised retargeting loss for motion prediction. Extensive experiments confirm its effectiveness on in‑domain and out‑of‑domain datasets.
By Yingdong Hu, Yisheng He, Jinnan Chen, Weihao Yuan, Kejie Qiu, Zehong Lin, Siyu Zhu, Zilong Dong, Steven Hoi, Jun Zhang
Real-world spatial intelligence requires agents to understand scenes from continuous video streams, where objects move, persist, disappear, and reappear over time. While recent spatial foundation models have enabled generalizable feed-forward 3D reconstruction, most streaming methods remain geometry-centric and lack temporally consistent object-level understanding.
RoGe is a new end‑to‑end framework for novel view synthesis that jointly learns an implicit 3D scene representation and a video diffusion model. It eliminates the need for explicit 3D intermediates by querying the implicit scene with camera rays to produce geometric features that condition the diffusion model. Experiments on DL3DV show that RoGe surpasses reconstruction‑based, generation‑based, and hybrid baselines in image quality and temporal consistency, and ablations confirm the benefits of ray‑queried features and joint training.
By Xiaolei Lang, Ze Kang, Zehao Huang, Naiyan Wang