中文
相关论文

相关论文: World-R1: Reinforcing 3D Constraints for Text-to-V…

200 篇论文

We present a novel method for generating geometrically realistic and consistent orbital videos from a single image of an object. Existing video generation works mostly rely on pixel-wise attention to enforce view consistency across frames.…

计算机视觉与模式识别 · 计算机科学 2026-04-15 Rong Wang , Ruyi Zha , Ziang Cheng , Jiayu Yang , Pulak Purkait , Hongdong Li

Despite impressive progress in video generation, existing models remain limited to surface-level plausibility, lacking a coherent and unified understanding of the world. Prior approaches typically incorporate only a single form of…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Boming Tan , Xiangdong Zhang , Ning Liao , Yuqing Zhang , Shaofeng Zhang , Xue Yang , Qi Fan , Yanyong Zhang

Large-scale flow matching models have achieved strong performance across generative tasks such as text-to-image, video, 3D, and speech synthesis. However, aligning their outputs with human preferences and task-specific objectives remains…

机器学习 · 计算机科学 2026-03-10 Zexiang Liu , Xianglong He , Yangguang Li

Camera-controlled video generation has achieved remarkable progress in recent years. However, existing video-to-video re-rendering methods primarily rely on Supervised Fine-Tuning using synthetic datasets. At present, there is an extreme…

计算机视觉与模式识别 · 计算机科学 2026-05-25 Zizun Li , Haoyu Guo , Runzhe Teng , Chunhua Shen , Tong He

Inspired by DeepSeek-R1's success in eliciting reasoning abilities through rule-based reinforcement learning (RL), we introduce Video-R1 as the first attempt to systematically explore the R1 paradigm for incentivizing video reasoning within…

计算机视觉与模式识别 · 计算机科学 2025-10-23 Kaituo Feng , Kaixiong Gong , Bohao Li , Zonghao Guo , Yibing Wang , Tianshuo Peng , Junfei Wu , Xiaoying Zhang , Benyou Wang , Xiangyu Yue

Emerging world models autoregressively generate video frames in response to actions, such as camera movements and text prompts, among other control signals. Due to limited temporal context window sizes, these models often struggle to…

计算机视觉与模式识别 · 计算机科学 2025-06-06 Tong Wu , Shuai Yang , Ryan Po , Yinghao Xu , Ziwei Liu , Dahua Lin , Gordon Wetzstein

Complex video reasoning remains a significant challenge for Multimodal Large Language Models (MLLMs), as current R1-based methodologies often prioritize text-centric reasoning derived from text-based and image-based developments. In video…

计算机视觉与模式识别 · 计算机科学 2025-11-18 Bo Fang , Yuxin Song , Qiangqiang Wu , Haoyuan Sun , Wenhao Wu , Antoni B. Chan

Videos inherently represent 2D projections of a dynamic 3D world. However, our analysis suggests that video diffusion models trained solely on raw video data often fail to capture meaningful geometric-aware structure in their learned…

计算机视觉与模式识别 · 计算机科学 2026-05-06 Haoyu Wu , Diankun Wu , Tianyu He , Junliang Guo , Yang Ye , Yueqi Duan , Jiang Bian

Recent advances in video world modeling have enabled large-scale generative models to simulate embodied environments with high visual fidelity, providing strong priors for prediction, planning, and control. Yet, despite their realism, these…

计算机视觉与模式识别 · 计算机科学 2026-02-10 Haoyang He , Jay Patrikar , Dong-Ki Kim , Max Smith , Daniel McGann , Ali-akbar Agha-mohammadi , Shayegan Omidshafiei , Sebastian Scherer

Large Vision-Language Models (LVLMs) have become powerful general-purpose assistants, yet their predictions often lack reliability and interpretability due to insufficient grounding in visual evidence. The emerging thinking-with-images…

计算机视觉与模式识别 · 计算机科学 2026-02-04 Meng Cao , Haoze Zhao , Can Zhang , Xiaojun Chang , Ian Reid , Xiaodan Liang

Video generation models produce visually coherent content but struggle with tasks requiring spatial reasoning and multi-step planning. Reinforcement learning (RL) offers a path to improve generalization, but its effectiveness in video…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Ming Liu , Yunbei Zhang , Shilong Liu , Liwen Wang , Wensheng Zhang

Recent advances in generative AI have revolutionized visual content creation, yet aligning model outputs with human preferences remains a critical challenge. While Reinforcement Learning (RL) has emerged as a promising approach for…

计算机视觉与模式识别 · 计算机科学 2025-08-29 Zeyue Xue , Jie Wu , Yu Gao , Fangyuan Kong , Lingting Zhu , Mengzhao Chen , Zhiheng Liu , Wei Liu , Qiushan Guo , Weilin Huang , Ping Luo

Producing long, coherent video sequences with stable 3D structure remains a major challenge, particularly in streaming scenarios. Motivated by this, we introduce Endless World, a real-time framework for infinite, 3D-consistent video…

计算机视觉与模式识别 · 计算机科学 2025-12-16 Ke Zhang , Yiqun Mei , Jiacong Xu , Vishal M. Patel

Generative models have made significant progress in synthesizing visual content, including images, videos, and 3D/4D structures. However, they are typically trained with surrogate objectives such as likelihood or reconstruction loss, which…

计算机视觉与模式识别 · 计算机科学 2026-01-21 Yuanzhi Liang , Yijie Fang , Ke Hao , Rui Li , Ziqi Ni , Ruijie Su , Chi Zhang

High-quality 3D world models are pivotal for embodied intelligence and Artificial General Intelligence (AGI), underpinning applications such as AR/VR content creation and robotic navigation. Despite the established strong imaginative…

计算机视觉与模式识别 · 计算机科学 2025-11-03 Yixiang Dai , Fan Jiang , Chiyu Wang , Mu Xu , Yonggang Qi

Currently, utilizing large language models to understand the 3D world is becoming popular. Yet existing 3D-aware LLMs act as black boxes: they output bounding boxes or textual answers without revealing how those decisions are made, and they…

计算机视觉与模式识别 · 计算机科学 2025-06-24 Zhihao Yuan , Shuyi Jiang , Chun-Mei Feng , Yaolun Zhang , Shuguang Cui , Zhen Li , Na Zhao

Previous works leveraging video models for image-to-3D scene generation tend to suffer from geometric distortions and blurry content. In this paper, we renovate the pipeline of image-to-3D scene generation by unlocking the potential of…

计算机视觉与模式识别 · 计算机科学 2025-12-01 Yuhao Wan , Lijuan Liu , Jingzhi Zhou , Zihan Zhou , Xuying Zhang , Dongbo Zhang , Shaohui Jiao , Qibin Hou , Ming-Ming Cheng

Recent works have demonstrated the effectiveness of reinforcement learning (RL)-based post-training for enhancing the reasoning capabilities of large language models (LLMs). In particular, Group Relative Policy Optimization (GRPO) has shown…

计算机视觉与模式识别 · 计算机科学 2026-02-05 Jinyoung Park , Jeehye Na , Jinyoung Kim , Hyunwoo J. Kim

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.…

机器人学 · 计算机科学 2026-03-27 Jai Bardhan , Patrik Drozdik , Josef Sivic , Vladimir Petrik

Long-horizon video-audio reasoning and fine-grained pixel understanding impose conflicting requirements on omnimodal models: dense temporal coverage demands many low-resolution frames, whereas precise grounding calls for high-resolution…

计算机视觉与模式识别 · 计算机科学 2025-05-27 Hao Zhong , Muzhi Zhu , Zongze Du , Zheng Huang , Canyu Zhao , Mingyu Liu , Wen Wang , Hao Chen , Chunhua Shen
‹ 上一页 1 2 3 10 下一页 ›