cs.CV（2024-12-07）

📊 共 16 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (6 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (5 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Text-to-3D Gaussian Splatting with Physics-Grounded Motion Generation	提出基于物理的运动生成Text-to-3D高斯溅射方法，提升3D模型真实感。	3D gaussian splatting gaussian splatting splatting
2	Temporally Compressed 3D Gaussian Splatting for Dynamic Scenes	提出时间压缩3D高斯溅射(TC3DGS)，用于动态场景的实时渲染和高效存储。	3D gaussian splatting 3DGS gaussian splatting	✅
3	Template-free Articulated Gaussian Splatting for Real-time Reposable Dynamic View Synthesis	提出一种免模板的铰接高斯溅射方法，用于实时可重构的动态视角合成	3D gaussian splatting gaussian splatting splatting
4	TB-HSU: Hierarchical 3D Scene Understanding with Contextual Affordances	提出基于Transformer的3D层级场景理解模型，融合上下文可供性。	scene understanding affordance
5	Radiant: Large-scale 3D Gaussian Rendering based on Hierarchical Framework	Radiant：基于分层框架的大规模3D高斯渲染，提升异构环境下的重建质量和效率。	3D gaussian splatting 3DGS gaussian splatting
6	Street Gaussians without 3D Object Tracker	提出Street Gaussians，无需3D物体追踪器即可实现驾驶场景下的真实场景重建。	scene reconstruction foundation model	✅

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

#	题目	一句话要点	标签	🔗	⭐
7	Segment-Level Road Obstacle Detection Using Visual Foundation Model Priors and Likelihood Ratios	提出基于视觉基础模型先验和似然比的分割级道路障碍物检测方法	foundation model
8	Biological Brain Age Estimation using Sex-Aware Adversarial Variational Autoencoder with Multimodal Neuroimages	提出基于性别感知的对抗变分自编码器，用于多模态神经影像的生物脑年龄估计。	multimodal
9	Dif4FF: Leveraging Multimodal Diffusion Models and Graph Neural Networks for Accurate New Fashion Product Performance Forecasting	Dif4FF：利用多模态扩散模型和图神经网络进行精准的新时尚产品性能预测	multimodal
10	GAF-FusionNet: Multimodal ECG Analysis via Gramian Angular Fields and Split Attention	GAF-FusionNet：利用格拉姆角场和分离注意力进行多模态心电图分析	multimodal	✅
11	Do We Need to Design Specific Diffusion Models for Different Tasks? Try ONE-PIC	提出ONE-PIC以简化扩散模型的任务适应问题	large language model	✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#	题目	一句话要点	标签	🔗	⭐
12	Compositional Image Retrieval via Instruction-Aware Contrastive Learning	提出基于指令感知对比学习的复合图像检索方法以解决数据稀缺问题	contrastive learning large language model multimodal
13	Multimodal Biometric Authentication Using Camera-Based PPG and Fingerprint Fusion	提出基于相机PPG和指纹融合的多模态生物特征认证系统，提升用户验证精度。	SSM multimodal
14	UMSPU: Universal Multi-Size Phase Unwrapping via Mutual Self-Distillation and Adaptive Boosting Ensemble Segmenters	提出UMSPU，通过互蒸馏和自适应Boosting集成分割器实现通用多尺寸相位解包裹	distillation
15	Neighborhood Commonality-aware Evolution Network for Continuous Generalized Category Discovery	提出Neighborhood Commonality-aware Evolution Network以解决连续类别发现问题	representation learning contrastive learning distillation	✅

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

#	题目	一句话要点	标签	🔗	⭐
16	STEAM-EEG: Spatiotemporal EEG Analysis with Markov Transfer Fields and Attentive CNNs	提出STEAM-EEG框架，利用马尔可夫转移场和注意力CNN进行时空脑电信号分析。	spatiotemporal

⬅️ 返回 cs.CV 首页 · 🏠 返回主页