cs.CV(2024-10-09)
📊 共 5 篇论文 | 🔗 4 篇有代码
🎯 兴趣领域导航
支柱三:空间感知与语义 (Perception & Semantics) (2 🔗2)
支柱九:具身大模型 (Embodied Foundation Models) (2 🔗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) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | ES-Gaussian: Gaussian Splatting Mapping via Error Space-Based Gaussian Completion | ES-Gaussian:基于误差空间的高斯补全,实现低成本高精度室内三维重建 | 3DGS gaussian splatting splatting | ✅ | |
| 2 | NeRF-Accelerated Ecological Monitoring in Mixed-Evergreen Redwood Forest | 利用NeRF加速混合常绿红木森林的生态监测,实现高效树木直径估计 | NeRF neural radiance field | ✅ |
🔬 支柱九:具身大模型 (Embodied Foundation Models) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 3 | Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology | 提出OpenUAV平台与UAV-Need-Help基准,解决无人机视觉-语言导航的真实性问题。 | VLN multimodal | ||
| 4 | Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate | 提出模态融合率(MIR)指标,用于评估大规模视觉语言模型(LVLM)预训练质量。 | large language model | ✅ |
🔬 支柱二:RL算法与架构 (RL & Architecture) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 5 | Positive-Augmented Contrastive Learning for Vision-and-Language Evaluation and Training | 提出PAC-S++,通过正样本增强对比学习提升视觉-语言评估与训练效果 | contrastive learning | ✅ |