cs.CV（2024-02-15）
📊 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) (5 🔗2)
支柱六：视频提取与匹配 (Video Extraction) (2)
支柱二：RL算法与架构 (RL & Architecture) (2)
支柱八：物理动画 (Physics-based Animation) (1)
支柱九：具身大模型 (Embodied Foundation Models) (1)
🔬 支柱三：空间感知与语义 (Perception & Semantics) (5 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Evaluating Neural Radiance Fields (NeRFs) for 3D Plant Geometry Reconstruction in Field Conditions | 评估NeRF技术以解决复杂环境下植物3D重建问题 | 3D reconstruction NeRF neural radiance field | ||
| 2 | GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splatting | 提出GaussianObject以解决稀疏视图下的3D重建问题 | gaussian splatting splatting | ✅ | |
| 3 | GES: Generalized Exponential Splatting for Efficient Radiance Field Rendering | 提出GES以解决高内存占用的3D场景渲染问题 | 3D gaussian splatting 3D reconstruction gaussian splatting | ||
| 4 | X-maps: Direct Depth Lookup for Event-based Structured Light Systems | 提出X-maps以解决事件相机深度估计效率问题 | depth estimation | ✅ | |
| 5 | What's in the Flow? Exploiting Temporal Motion Cues for Unsupervised Generic Event Boundary Detection | 提出FlowGEBD以解决无监督通用事件边界检测问题 | optical flow |
🔬 支柱六：视频提取与匹配 (Video Extraction) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 6 | The Visual Experience Dataset: Over 200 Recorded Hours of Integrated Eye Movement, Odometry, and Egocentric Video | 提出视觉体验数据集以促进视觉感知研究 | egocentric spatiotemporal | ||
| 7 | Region Feature Descriptor Adapted to High Affine Transformations | 提出区域特征描述符以解决高仿射变换下特征匹配问题 | feature matching |
🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 8 | MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations | 提出MIM-Refiner以提升预训练MIM模型的对比学习效果 | contrastive learning | ||
| 9 | MM-Point: Multi-View Information-Enhanced Multi-Modal Self-Supervised 3D Point Cloud Understanding | 提出MM-Point以解决3D点云理解中的多模态信息整合问题 | representation learning contrastive learning |
🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 10 | Spatiotemporal Disentanglement of Arteriovenous Malformations in Digital Subtraction Angiography | 提出基于双模型的DSA图像自动分类方法以改善AVM可视化 | spatiotemporal |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 11 | LLMs as Bridges: Reformulating Grounded Multimodal Named Entity Recognition | 提出RiVEG框架以解决GMNER任务中的多模态实体识别问题 | large language model multimodal visual grounding |