cs.CV(2024-06-11)

📊 共 6 篇论文

🎯 兴趣领域导航

支柱三:空间感知与语义 (Perception & Semantics) (3) 支柱一:机器人控制 (Robot Control) (2) 支柱九:具身大模型 (Embodied Foundation Models) (1)

🔬 支柱三:空间感知与语义 (Perception & Semantics) (3 篇)

#题目一句话要点标签🔗
1 Trim 3D Gaussian Splatting for Accurate Geometry Representation 提出TrimGS,通过高斯裁剪实现精确3D几何重建 3D gaussian splatting 3DGS gaussian splatting
2 ROADWork: A Dataset and Benchmark for Learning to Recognize, Observe, Analyze and Drive Through Work Zones ROADWork:用于学习识别、观察、分析和驾驶通过施工区域的数据集与基准 open-vocabulary open vocabulary foundation model
3 Neural Visibility Field for Uncertainty-Driven Active Mapping 提出神经可见性场(NVF),用于不确定性驱动的主动地图构建。 NeRF neural radiance field scene reconstruction

🔬 支柱一:机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗
4 RACon: Retrieval-Augmented Simulated Character Locomotion Control 提出RACon,一种检索增强的模拟角色运动控制方法,提升用户控制响应性。 locomotion manipulation reinforcement learning
5 Visual Representation Learning with Stochastic Frame Prediction 提出基于随机帧预测的视觉表征学习框架,提升视频理解和机器人学习任务性能 locomotion manipulation representation learning

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

#题目一句话要点标签🔗
6 VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs VideoLLaMA 2:通过时空建模和音频理解增强视频大语言模型 large language model multimodal

⬅️ 返回 cs.CV 首页 · 🏠 返回主页