cs.CV（2024-01-23）

📊 共 18 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) (10 🔗4) 支柱九：具身大模型 (Embodied Foundation Models) (4 🔗1) 支柱八：物理动画 (Physics-based Animation) (2 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (10 篇)

#题目一句话要点标签🔗⭐
1 Icy Moon Surface Simulation and Stereo Depth Estimation for Sampling Autonomy 提出GUISS框架以解决冰月表面采样自主性问题 depth estimation stereo depth ✅
2 EndoGaussian: Real-time Gaussian Splatting for Dynamic Endoscopic Scene Reconstruction 提出EndoGaussian以解决动态内窥镜场景重建问题 depth estimation 3D gaussian splatting 3DGS ✅
3 NeRF-AD: Neural Radiance Field with Attention-based Disentanglement for Talking Face Synthesis 提出NeRF-AD以解决音频驱动的说话人脸合成问题 NeRF neural radiance field multimodal ✅
4 Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models 提出综合可供性模型以解决人机交互理解不足问题 affordance human-object interaction HOI
5 Training-Free Action Recognition and Goal Inference with Dynamic Frame Selection 提出VidTFS框架以解决训练需求的动作识别与目标推断问题 open-vocabulary open vocabulary large language model
6 Exploration and Improvement of Nerf-based 3D Scene Editing Techniques 提出基于NeRF的3D场景编辑技术以解决高计算成本问题 NeRF multimodal
7 FedRSU: Federated Learning for Scene Flow Estimation on Roadside Units 提出FedRSU框架以解决RSU数据利用不足问题 scene flow
8 Digital Divides in Scene Recognition: Uncovering Socioeconomic Biases in Deep Learning Systems 揭示深度学习系统中的社会经济偏见以改善场景识别 scene understanding
9 RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos 提出WildRGB-D数据集以提升真实场景3D物体学习能力 6D pose estimation ✅
10 Methods and strategies for improving the novel view synthesis quality of neural radiation field 提出改进神经辐射场新视图合成质量的方法与策略 NeRF

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
11 DatUS^2: Data-driven Unsupervised Semantic Segmentation with Pre-trained Self-supervised Vision Transformer 提出DatUS^2以解决无监督语义分割问题 foundation model
12 MUSES: The Multi-Sensor Semantic Perception Dataset for Driving under Uncertainty 提出MUSES数据集以解决自动驾驶中的多传感器语义感知问题 multimodal
13 CCA: Collaborative Competitive Agents for Image Editing 提出协作竞争代理模型以增强图像编辑能力 large language model ✅
14 AdaEmbed: Semi-supervised Domain Adaptation in the Embedding Space 提出AdaEmbed以解决半监督领域适应问题 foundation model

🔬 支柱八：物理动画 (Physics-based Animation) (2 篇)

#题目一句话要点标签🔗⭐
15 Deep Spatiotemporal Clutter Filtering of Transthoracic Echocardiographic Images: Leveraging Contextual Attention and Residual Learning 提出深度卷积自编码器以解决超声心动图图像中的混响干扰问题 spatiotemporal ✅
16 Convolutional Initialization for Data-Efficient Vision Transformers 提出卷积初始化策略以提升小数据集上视觉变换器性能 PULSE

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

#题目一句话要点标签🔗⭐
17 HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments 提出HAZARD基准以解决动态环境中的决策问题 reinforcement learning large language model

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

#题目一句话要点标签🔗⭐
18 PSDF: Prior-Driven Neural Implicit Surface Learning for Multi-view Reconstruction 提出PSDF以解决多视图重建中的几何不一致问题 geometric consistency

⬅️ 返回 cs.CV 首页 · 🏠 返回主页