cs.CV（2024-05-17）

📊 共 11 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (4 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱九：具身大模型 (Embodied Foundation Models) (2 🔗1) 支柱四：生成式动作 (Generative Motion) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (4 篇)

#题目一句话要点标签🔗⭐
1 Enhanced 3D Urban Scene Reconstruction and Point Cloud Densification using Gaussian Splatting and Google Earth Imagery 提出基于高斯点云和谷歌地球影像的3D城市场景重建方法 3D gaussian splatting gaussian splatting splatting
2 ART3D: 3D Gaussian Splatting for Text-Guided Artistic Scenes Generation ART3D：提出基于3D高斯溅射的文本引导艺术场景生成框架 3D gaussian splatting gaussian splatting splatting
3 FA-Depth: Toward Fast and Accurate Self-supervised Monocular Depth Estimation FA-Depth：面向快速且精确的自监督单目深度估计 depth estimation monocular depth ✅
4 Open-Vocabulary Spatio-Temporal Action Detection 提出开放词汇时空动作检测，利用预训练视频-语言模型提升泛化性。 open-vocabulary open vocabulary

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
5 SignLLM: Sign Language Production Large Language Models 提出SignLLM：多语种手语生成大语言模型，实现文本到手语的转换 reinforcement learning large language model
6 Automated Radiology Report Generation: A Review of Recent Advances 综述性论文：回顾自动放射报告生成（ARRG）的最新进展与未来方向。 reinforcement learning contrastive learning multimodal
7 Accurate Training Data for Occupancy Map Prediction in Automated Driving Using Evidence Theory 提出基于证据理论的LiDAR点云重建方法，提升自动驾驶场景 occupancy map 预测精度。 MAE occupancy grid

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗⭐
8 Efficient Multimodal Large Language Models: A Survey 综述高效多模态大语言模型，探索边缘计算场景下的轻量化方案。 large language model multimodal ✅
9 Safeguarding Vision-Language Models Against Patched Visual Prompt Injectors 提出SmoothVLM，防御视觉语言模型中基于对抗补丁的提示注入攻击 large language model multimodal

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
10 Flexible Motion In-betweening with Diffusion Models 提出CondMDI，利用扩散模型实现灵活的关键帧人体动作插值生成。 motion diffusion human motion character animation

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
11 Reconstruction of Manipulated Garment with Guided Deformation Prior 提出基于扩散先验引导的服装重建方法，解决操纵状态下服装三维重建问题 manipulation

⬅️ 返回 cs.CV 首页 · 🏠 返回主页