cs.CV（2024-03-07）

📊 共 18 篇论文 | 🔗 8 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (7 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗1) 支柱一：机器人控制 (Robot Control) (2) 支柱七：动作重定向 (Motion Retargeting) (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 Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesis 提出X-Gaussian以解决X射线新视角合成问题 3D gaussian splatting gaussian splatting splatting ✅
2 BAGS: Blur Agnostic Gaussian Splatting through Multi-Scale Kernel Modeling 提出BAGS以解决图像模糊下的高质量场景重建问题 gaussian splatting splatting neural radiance field
3 Finding Waldo: Towards Efficient Exploration of NeRF Scene Spaces 提出场景探索框架以优化NeRF模型输入发现 3D reconstruction NeRF neural radiance field
4 Out of the Room: Generalizing Event-Based Dynamic Motion Segmentation for Complex Scenes 提出一种事件驱动的方法以解决复杂场景中的动态运动分割问题 monocular depth scene understanding optical flow
5 Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed 提出高效LoFTR以解决半稠密特征匹配速度慢的问题 3D reconstruction feature matching ✅
6 I Can't Believe It's Not Scene Flow! 提出Bucket Normalized EPE以解决小物体运动评估问题 scene flow ✅
7 CN-RMA: Combined Network with Ray Marching Aggregation for 3D Indoors Object Detection from Multi-view Images 提出CN-RMA以解决多视角图像中的3D室内物体检测问题 3D reconstruction ✅

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

#题目一句话要点标签🔗⭐
8 CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios 提出CAT以解决动态音视频场景中的问答挑战 direct preference optimization large language model multimodal ✅
9 Möbius Transform for Mitigating Perspective Distortions in Representation Learning 提出Möbius变换以缓解表示学习中的透视失真问题 representation learning spatial relationship ✅
10 Self-Adapting Large Visual-Language Models to Edge Devices across Visual Modalities 提出EdgeVL框架以解决边缘设备上视觉语言模型适应性问题 contrastive learning distillation open-vocabulary

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#题目一句话要点标签🔗⭐
11 SnapNTell: Enhancing Entity-Centric Visual Question Answering with Retrieval Augmented Multimodal LLM 提出SnapNTell以解决长尾实体视觉问答问题 multimodal
12 TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document 提出TextMonkey以解决文档理解中的OCR依赖问题 multimodal ✅
13 $\text{R}^2$-Bench: Benchmarking the Robustness of Referring Perception Models under Perturbations 提出R^2-Bench以评估指向感知模型的鲁棒性 multimodal

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
14 A spatiotemporal style transfer algorithm for dynamic visual stimulus generation 提出时空风格迁移算法以生成动态视觉刺激 manipulation spatiotemporal
15 StableDrag: Stable Dragging for Point-based Image Editing 提出StableDrag以解决点基图像编辑中的不稳定性问题 manipulation

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

#题目一句话要点标签🔗⭐
16 Fooling Neural Networks for Motion Forecasting via Adversarial Attacks 通过对抗攻击提升人类运动预测模型的鲁棒性 human motion human motion prediction motion prediction

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

#题目一句话要点标签🔗⭐
17 Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose Estimation 提出单视图到双视图适应方法以解决3D手势估计问题 egocentric egocentric vision ✅

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

#题目一句话要点标签🔗⭐
18 Spatiotemporal Pooling on Appropriate Topological Maps Represented as Two-Dimensional Images for EEG Classification 提出基于EEG信号的运动想象分类新方法以提升准确率 spatiotemporal

⬅️ 返回 cs.CV 首页 · 🏠 返回主页