cs.CV(2025-10-24)

📊 共 6 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱二:RL算法与架构 (RL & Architecture) (2) 支柱三:空间感知与语义 (Perception & Semantics) (1) 支柱九:具身大模型 (Embodied Foundation Models) (1) 支柱一:机器人控制 (Robot Control) (1) 支柱七:动作重定向 (Motion Retargeting) (1 🔗1)

🔬 支柱二:RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗
1 PhysWorld: From Real Videos to World Models of Deformable Objects via Physics-Aware Demonstration Synthesis PhysWorld:通过物理感知演示合成,从真实视频构建可变形对象的交互式世界模型 world model physically plausible
2 WorldGrow: Generating Infinite 3D World 提出WorldGrow以解决无限扩展3D世界生成问题 world model implicit representation foundation model

🔬 支柱三:空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗
3 ZING-3D: Zero-shot Incremental 3D Scene Graphs via Vision-Language Models ZING-3D:利用视觉-语言模型实现零样本增量式3D场景图构建 open-vocabulary open vocabulary spatial relationship

🔬 支柱九:具身大模型 (Embodied Foundation Models) (1 篇)

#题目一句话要点标签🔗
4 Head Pursuit: Probing Attention Specialization in Multimodal Transformers 通过探究注意力头专业化,理解和控制多模态Transformer模型 multimodal

🔬 支柱一:机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗
5 ArtiLatent: Realistic Articulated 3D Object Generation via Structured Latents ArtiLatent:通过结构化隐空间生成逼真可动3D物体 manipulation physically plausible geometric consistency

🔬 支柱七:动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗
6 Group Inertial Poser: Multi-Person Pose and Global Translation from Sparse Inertial Sensors and Ultra-Wideband Ranging Group Inertial Poser:融合稀疏IMU与UWB的多人姿态与全局位姿估计 human motion

⬅️ 返回 cs.CV 首页 · 🏠 返回主页