cs.CV（2024-09-23）
📊 共 7 篇论文 | 🔗 3 篇有代码
🎯 兴趣领域导航
支柱九：具身大模型 (Embodied Foundation Models) (3 🔗1)
支柱三：空间感知与语义 (Perception & Semantics) (3 🔗1)
支柱二：RL算法与架构 (RL & Architecture) (1 🔗1)
🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | ReVLA: Reverting Visual Domain Limitation of Robotic Foundation Models | ReVLA：通过模型融合逆转机器人视觉基础模型的视觉领域限制 | vision-language-action large language model foundation model | ||
| 2 | Dynamic Realms: 4D Content Analysis, Recovery and Generation with Geometric, Topological and Physical Priors | 利用几何、拓扑和物理先验实现高效高质量的4D内容分析、恢复与生成 | embodied AI | ||
| 3 | FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension | 提出FineCops-Ref数据集与任务，用于细粒度组合指代表达式理解，挑战多模态大模型 | large language model | ✅ |
🔬 支柱三：空间感知与语义 (Perception & Semantics) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 4 | GroCo: Ground Constraint for Metric Self-Supervised Monocular Depth | GroCo：提出基于地面约束的自监督单目深度估计方法，提升尺度恢复和泛化性。 | depth estimation monocular depth metric depth | ||
| 5 | FisheyeDepth: A Real Scale Self-Supervised Depth Estimation Model for Fisheye Camera | FisheyeDepth：为鱼眼相机设计的真实尺度自监督深度估计模型 | depth estimation | ✅ | |
| 6 | Human Hair Reconstruction with Strand-Aligned 3D Gaussians | 提出Gaussian Haircut，利用对齐发丝的3D高斯重建逼真发型 | 3D gaussian splatting gaussian splatting splatting |
🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 7 | TextToon: Real-Time Text Toonify Head Avatar from Single Video | TextToon：提出一种基于单目视频的实时文本驱动卡通头像生成方法 | contrastive learning 3D gaussian splatting gaussian splatting | ✅ |