cs.CV(2024-12-02)

📊 共 11 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱三:空间感知与语义 (Perception & Semantics) (8) 支柱六:视频提取与匹配 (Video Extraction) (1) 支柱一:机器人控制 (Robot Control) (1) 支柱二:RL算法与架构 (RL & Architecture) (1 🔗1)

🔬 支柱三:空间感知与语义 (Perception & Semantics) (8 篇)

#题目一句话要点标签🔗
1 GFreeDet: Exploiting Gaussian Splatting and Foundation Models for Model-free Unseen Object Detection in the BOP Challenge 2024 GFreeDet:利用高斯溅射和基础模型实现BOP挑战赛2024中的无模型未见物体检测 gaussian splatting splatting foundation model
2 6DOPE-GS: Online 6D Object Pose Estimation using Gaussian Splatting 6DOPE-GS:利用高斯溅射实现实时6D物体姿态估计与跟踪 gaussian splatting splatting
3 The Bare Necessities: Designing Simple, Effective Open-Vocabulary Scene Graphs 优化3D开放词汇场景图:提升效率与性能,降低计算成本 open-vocabulary open vocabulary
4 HDGS: Textured 2D Gaussian Splatting for Enhanced Scene Rendering 提出HDGS,通过纹理化2D高斯溅射增强场景渲染效果 gaussian splatting splatting
5 CTRL-D: Controllable Dynamic 3D Scene Editing with Personalized 2D Diffusion CTRL-D:基于个性化2D扩散模型的可控动态3D场景编辑 3D gaussian splatting gaussian splatting splatting
6 HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Driving HUGSIM:用于自动驾驶的实时、照片级真实感和闭环仿真器 3D gaussian splatting gaussian splatting splatting
7 Look Ma, No Ground Truth! Ground-Truth-Free Tuning of Structure from Motion and Visual SLAM 提出无地面真值的评估方法以解决SfM和VSLAM的依赖问题 visual SLAM
8 One Shot, One Talk: Whole-body Talking Avatar from a Single Image 提出一种基于单张图像生成全身可控说话人像的方法 3DGS

🔬 支柱六:视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗
9 HandOS: 3D Hand Reconstruction in One Stage HandOS:提出单阶段3D手部重建框架,提升效率并避免累积误差。 Ego4D hand reconstruction

🔬 支柱一:机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗
10 Articulate3D: Holistic Understanding of 3D Scenes as Universal Scene Description Articulate3D:提出通用场景描述的3D场景整体理解框架,聚焦可交互物体的部件分割与运动属性预测。 manipulation scene understanding embodied AI

🔬 支柱二:RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗
11 COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training COSMOS:跨模态自蒸馏视觉语言预训练,提升下游任务性能 distillation

⬅️ 返回 cs.CV 首页 · 🏠 返回主页