English
Related papers

Related papers: MVISTA-4D: View-Consistent 4D World Model with Tes…

200 papers

Advances in generative modeling have significantly enhanced digital content creation, extending from 2D images to complex 3D and 4D scenes. Despite substantial progress, producing high-fidelity and temporally consistent dynamic 4D content…

Computer Vision and Pattern Recognition · Computer Science 2025-08-01 DongFu Yin , Xiaotian Chen , Fei Richard Yu , Xuanchen Li , Xinhao Zhang

Robotic manipulation in unstructured environments requires systems that can generalize across diverse tasks while maintaining robust and reliable performance. We introduce {GVF-TAPE}, a closed-loop framework that combines generative visual…

Robotics · Computer Science 2025-09-03 Chuye Zhang , Xiaoxiong Zhang , Wei Pan , Linfang Zheng , Wei Zhang

We pose a new problem, In-2-4D, for generative 4D (i.e., 3D + motion) inbetweening to interpolate two single-view images. In contrast to video/4D generation from only text or a single image, our interpolative task can leverage more precise…

Graphics · Computer Science 2025-09-30 Sauradip Nag , Daniel Cohen-Or , Hao Zhang , Ali Mahdavi-Amiri

Dynamic scene reconstruction in autonomous driving remains a fundamental challenge due to significant temporal variations, moving objects, and complex scene dynamics. Existing feed-forward 3D models have demonstrated strong performance in…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Zhuolin He , Jing Li , Guanghao Li , Xiaolei Chen , Jiacheng Tang , Siyang Zhang , Zhounan Jin , Feipeng Cai , Bin Li , Jian Pu , Jia Cai , Xiangyang Xue

Reconstructing dynamic 4D scenes is an important yet challenging task. While 3D foundation models like VGGT excel in static settings, they often struggle with dynamic sequences where motion causes significant geometric ambiguity. To address…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Ying Zang , Yidong Han , Chaotao Ding , Yuanqi Hu , Deyi Ji , Qi Zhu , Xuanfu Li , Jin Ma , Lingyun Sun , Tianrun Chen , Lanyun Zhu

We present MVD-Fusion: a method for single-view 3D inference via generative modeling of multi-view-consistent RGB-D images. While recent methods pursuing 3D inference advocate learning novel-view generative models, these generations are not…

Computer Vision and Pattern Recognition · Computer Science 2024-04-05 Hanzhe Hu , Zhizhuo Zhou , Varun Jampani , Shubham Tulsiani

A key challenge in manipulation is learning a policy that can robustly generalize to diverse visual environments. A promising mechanism for learning robust policies is to leverage video generative models, which are pretrained on large-scale…

Active perception in vision-based robotic manipulation aims to move the camera toward more informative observation viewpoints, thereby providing high-quality perceptual inputs for downstream tasks. Most existing active perception methods…

Robotics · Computer Science 2026-01-21 Deyun Qin , Zezhi Liu , Hanqian Luo , Xiao Liang , Yongchun Fang

The vision-language-action (VLA) paradigm has enabled powerful robotic control by leveraging vision-language models, but its reliance on large-scale, high-quality robot data limits its generalization. Generative world models offer a…

Robotics · Computer Science 2026-01-27 Weishi Mi , Yong Bao , Xiaowei Chi , Xiaozhu Ju , Zhiyuan Qin , Kuangzhi Ge , Kai Tang , Peidong Jia , Shanghang Zhang , Jian Tang

In this work, we introduce a novel approach for creating controllable dynamics in 3D-generated Gaussians using casually captured reference videos. Our method transfers the motion of objects from reference videos to a variety of generated 3D…

Computer Vision and Pattern Recognition · Computer Science 2024-07-09 Zhoujie Fu , Jiacheng Wei , Wenhao Shen , Chaoyue Song , Xiaofeng Yang , Fayao Liu , Xulei Yang , Guosheng Lin

Action-conditioned robot world models generate future video frames of the manipulated scene given a robot action sequence, offering a promising alternative for simulating tasks that are difficult to model with traditional physics engines.…

Robotics · Computer Science 2026-03-27 Jai Bardhan , Patrik Drozdik , Josef Sivic , Vladimir Petrik

Video generation models offer a promising imagination mechanism for robot manipulation by predicting long-horizon future observations, but effectively exploiting these imagined futures for action execution remains challenging. Existing…

Robotics · Computer Science 2026-05-13 Yajie Li , Bozhou Zhang , Chun Gu , Zipei Ma , Jiahui Zhang , Jiankang Deng , Xiatian Zhu , Li Zhang

Recent vision-language-action (VLA) models rely on 2D inputs, lacking integration with the broader realm of the 3D physical world. Furthermore, they perform action prediction by learning a direct mapping from perception to action,…

Computer Vision and Pattern Recognition · Computer Science 2024-03-15 Haoyu Zhen , Xiaowen Qiu , Peihao Chen , Jincheng Yang , Xin Yan , Yilun Du , Yining Hong , Chuang Gan

We present WorldVLA, an autoregressive action world model that unifies action and image understanding and generation. Our WorldVLA intergrates Vision-Language-Action (VLA) model and world model in one single framework. The world model…

Robotics · Computer Science 2025-06-27 Jun Cen , Chaohui Yu , Hangjie Yuan , Yuming Jiang , Siteng Huang , Jiayan Guo , Xin Li , Yibing Song , Hao Luo , Fan Wang , Deli Zhao , Hao Chen

Vision-language-action (VLA) policies have advanced language-conditioned robotic manipulation by transferring semantic priors from pretrained vision-language models to action generation. However, standard action-imitation learning often…

Robotics · Computer Science 2026-05-29 Zijian Zhang , Yuqing Jiang , Qian Cheng , Xiaofan Li , Si Liu , Ding Zhao , Ping Luo , Weitao Zhou , Haibao Yu

Unlike quasi-static robotic manipulation tasks like pick-and-place, dynamic tasks such as non-prehensile manipulation pose greater challenges, especially for vision-based control. Successful control requires the extraction of features…

Visual imitation learning enables robotic agents to acquire skills by observing expert demonstration videos. In the one-shot setting, the agent generates a policy after observing a single expert demonstration without additional fine-tuning.…

Robotics · Computer Science 2026-01-01 Raktim Gautam Goswami , Prashanth Krishnamurthy , Yann LeCun , Farshad Khorrami

Bimanual manipulation requires policies that can reason about 3D geometry, anticipate how it evolves under action, and generate smooth, coordinated motions. However, existing methods typically rely on 2D features with limited spatial…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Chongyang Xu , Haipeng Li , Shen Cheng , Jingyu Hu , Haoqiang Fan , Ziliang Feng , Shuaicheng Liu

Multi-view image generation holds significant application value in computer vision, particularly in domains like 3D reconstruction, virtual reality, and augmented reality. Most existing methods, which rely on extending single images, face…

Computer Vision and Pattern Recognition · Computer Science 2025-11-20 Jiaqi Wu , Yaosen Chen , Shuyuan Zhu

World models allow autonomous agents to plan and explore by predicting the visual outcomes of different actions. However, for robot manipulation, it is challenging to accurately model the fine-grained robot-object interaction within the…

Robotics · Computer Science 2025-07-30 Fangqi Zhu , Hongtao Wu , Song Guo , Yuxiao Liu , Chilam Cheang , Tao Kong