cs.CV（2024-04-29）

📊 共 21 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) (7 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗1) 支柱七：动作重定向 (Motion Retargeting) (2) 支柱一：机器人控制 (Robot Control) (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 SAGS: Structure-Aware 3D Gaussian Splatting 提出结构感知的3D高斯点云渲染方法以解决现有方法的局限性 3D gaussian splatting gaussian splatting splatting ✅
2 3D Gaussian Splatting with Deferred Reflection 提出延迟反射方法以解决高频反射场的渲染问题 3D gaussian splatting gaussian splatting splatting
3 GSTalker: Real-time Audio-Driven Talking Face Generation via Deformable Gaussian Splatting 提出GSTalker以解决音频驱动的实时人脸生成问题 gaussian splatting splatting NeRF
4 Reconstructing Satellites in 3D from Amateur Telescope Images 提出一种新框架以从业余望远镜图像重建3D卫星模型 3D reconstruction gaussian splatting splatting
5 MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editing 提出MeGA以解决高保真头部渲染与编辑问题 3D gaussian splatting gaussian splatting splatting
6 Simple-RF: Regularizing Sparse Input Radiance Fields with Simpler Solutions 提出Simple-RF以解决稀疏输入下的辐射场深度估计问题 NeRF neural radiance field implicit representation
7 Q-GroundCAM: Quantifying Grounding in Vision Language Models via GradCAM 提出Q-GroundCAM以量化视觉语言模型的基础能力 scene understanding

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
8 DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing 提出直接高斯3D编辑方法以解决多视角一致性问题 distillation 3D gaussian splatting gaussian splatting
9 Context Matters: Leveraging Spatiotemporal Metadata for Semi-Supervised Learning on Remote Sensing Images 提出利用时空元数据提升遥感图像半监督学习的伪标签质量 teacher-student distillation spatiotemporal
10 Embedded Representation Learning Network for Animating Styled Video Portrait 提出ERLNet以解决风格可控的谈话头生成问题 representation learning NeRF neural radiance field
11 Spectral-Spatial Mamba for Hyperspectral Image Classification 提出光谱空间Mamba以解决高光谱图像分类中的计算复杂性问题 Mamba state space model HSI
12 RSCaMa: Remote Sensing Image Change Captioning with State Space Model 提出RSCaMa模型以解决遥感图像变化描述中的时空建模问题 Mamba SSM state space model ✅
13 Visual Mamba: A Survey and New Outlooks 提出Mamba模型以解决长序列建模挑战 Mamba state space model ✅
14 ConPro: Learning Severity Representation for Medical Images using Contrastive Learning and Preference Optimization 提出ConPrO以解决医学图像严重性评估问题 representation learning contrastive learning

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

#题目一句话要点标签🔗⭐
15 Hallucination of Multimodal Large Language Models: A Survey 综述多模态大语言模型的幻觉现象及其解决方案 large language model multimodal ✅
16 EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatars 提出EMOPortraits以解决面部表情表达不足问题 multimodal
17 Enhancing Interactive Image Retrieval With Query Rewriting Using Large Language Models and Vision Language Models 提出交互式图像检索系统以解决传统方法的局限性 large language model

🔬 支柱七：动作重定向 (Motion Retargeting) (2 篇)

#题目一句话要点标签🔗⭐
18 4D-DRESS: A 4D Dataset of Real-world Human Clothing with Semantic Annotations 提出4D-DRESS以解决真实人类服装数据不足问题 human motion
19 Self-Avatar Animation in Virtual Reality: Impact of Motion Signals Artifacts on the Full-Body Pose Reconstruction 提出自我头像动画方法以解决虚拟现实中的全身姿态重建问题 motion reconstruction

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
20 $ν$-DBA: Neural Implicit Dense Bundle Adjustment Enables Image-Only Driving Scene Reconstruction 提出ν-DBA以解决自动驾驶场景重建问题 trajectory optimization implicit representation scene reconstruction

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

#题目一句话要点标签🔗⭐
21 OCK: Unsupervised Dynamic Video Prediction with Object-Centric Kinematics 提出OCK模型以解决动态视频预测中的运动动态建模问题 spatiotemporal

⬅️ 返回 cs.CV 首页 · 🏠 返回主页