cs.CV（2024-01-31）

📊 共 17 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (7 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (5 🔗4) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱六：视频提取与匹配 (Video Extraction) (1 🔗1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (7 篇)

#题目一句话要点标签🔗⭐
1 Exploring the Common Appearance-Boundary Adaptation for Nighttime Optical Flow 提出共同外观-边界适应框架以解决夜间光流问题 optical flow feature matching spatiotemporal
2 SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decomposition 提出SAGD以解决3D高斯分割边界模糊问题 3D gaussian splatting gaussian splatting splatting
3 Local Feature Matching Using Deep Learning: A Survey 综述深度学习在局部特征匹配中的应用与挑战 3D reconstruction feature matching ✅
4 ReplaceAnything3D:Text-Guided 3D Scene Editing with Compositional Neural Radiance Fields 提出ReplaceAnything3D以解决3D场景中对象替换问题 neural radiance field
5 CMRNext: Camera to LiDAR Matching in the Wild for Localization and Extrinsic Calibration 提出CMRNext以解决相机与LiDAR匹配问题 optical flow
6 Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimators 提出运动引导技术以解决扩散模型精细编辑问题 optical flow
7 Topology-Aware Latent Diffusion for 3D Shape Generation 提出拓扑感知潜在扩散模型以生成多样化3D形状 implicit representation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
8 Binding Touch to Everything: Learning Unified Multimodal Tactile Representations 提出UniTouch以解决多模态触觉学习挑战 multimodal ✅
9 Proximity QA: Unleashing the Power of Multi-Modal Large Language Models for Spatial Proximity Analysis 提出Proximity QA以解决多模态大语言模型空间接近性分析问题 large language model ✅
10 From Training-Free to Adaptive: Empirical Insights into MLLMs' Understanding of Detection Information 提出自适应训练方法以提升多模态大语言模型的检测信息理解能力 large language model multimodal
11 Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation 提出Hi-SAM以解决层次文本分割问题 foundation model ✅
12 M2-RAAP: A Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards Effective and Efficient Zero-shot Video-text Retrieval 提出M2-RAAP以解决视频-文本检索中的适应性预训练问题 foundation model ✅

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
13 Is Registering Raw Tagged-MR Enough for Strain Estimation in the Era of Deep Learning? 提出模型以解决标签MRI中标签褪色问题 motion estimation PULSE

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
14 PVLR: Prompt-driven Visual-Linguistic Representation Learning for Multi-Label Image Recognition 提出PVLR框架以提升多标签图像识别性能 representation learning

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
15 VR-based generation of photorealistic synthetic data for training hand-object tracking models 提出blender-hoisynth以解决手-物体交互数据标注不足问题 HOI

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
16 Improved Scene Landmark Detection for Camera Localization 提出改进的场景地标检测以解决相机定位精度不足问题 feature matching ✅

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
17 3D-Plotting Algorithm for Insects using YOLOv5 提出一种基于YOLOv5的3D昆虫监测算法以解决生态研究问题 spatiotemporal

⬅️ 返回 cs.CV 首页 · 🏠 返回主页