cs.CV（2024-02-01）

📊 共 20 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) (7 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (5 🔗1) 支柱四：生成式动作 (Generative Motion) (3) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗2) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱一：机器人控制 (Robot Control) (1 🔗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 On the Error Analysis of 3D Gaussian Splatting and an Optimal Projection Strategy 提出优化投影策略以解决3D高斯溅射中的投影误差问题 3D gaussian splatting gaussian splatting splatting
2 360-GS: Layout-guided Panoramic Gaussian Splatting For Indoor Roaming 提出360-GS以解决全景图像高质量渲染问题 3D gaussian splatting gaussian splatting splatting
3 ViCA-NeRF: View-Consistency-Aware 3D Editing of Neural Radiance Fields 提出ViCA-NeRF以解决3D编辑中的视图一致性问题 NeRF neural radiance field
4 GaussianStyle: Gaussian Head Avatar via StyleGAN 提出GaussianStyle以解决动态头建模中的细粒度表示和可扩展性问题 3D gaussian splatting 3DGS gaussian splatting
5 Diffusion-based Light Field Synthesis 提出LFdiff以解决光场合成的高成本问题 depth estimation monocular depth 3D reconstruction
6 Enhanced fringe-to-phase framework using deep learning 提出SFNet以解决有限条纹模式下的3D重建问题 3D reconstruction ✅
7 DRSM: efficient neural 4d decomposition for dynamic reconstruction in stationary monocular cameras 提出DRSM以解决单视角动态场景重建问题 scene reconstruction

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

#题目一句话要点标签🔗⭐
8 Safety of Multimodal Large Language Models on Images and Texts 系统评估多模态大语言模型在图像和文本上的安全性 large language model multimodal ✅
9 MEIA: Multimodal Embodied Perception and Interaction in Unknown Environments 提出MEIA以解决多模态智能体在未知环境中的交互问题 large language model multimodal
10 InfMAE: A Foundation Model in the Infrared Modality 提出InfMAE以解决红外模态基础模型构建问题 foundation model
11 Disentangled Multimodal Brain MR Image Translation via Transformer-based Modality Infuser 提出基于Transformer的模态融合方法以解决多模态脑MR图像合成问题 multimodal
12 SCO-VIST: Social Interaction Commonsense Knowledge-based Visual Storytelling 提出SCO-VIST框架以解决视觉故事生成中的社交常识问题 visual grounding

🔬 支柱四：生成式动作 (Generative Motion) (3 篇)

#题目一句话要点标签🔗⭐
13 IMUGPT 2.0: Language-Based Cross Modality Transfer for Sensor-Based Human Activity Recognition 提出IMUGPT 2.0以解决人类活动识别中的数据稀缺问题 text-driven motion motion synthesis large language model
14 AnimateLCM: Computation-Efficient Personalized Style Video Generation without Personalized Video Data 提出AnimateLCM以解决个性化视频生成效率低下问题 motion generation
15 Dynamic Texture Transfer using PatchMatch and Transformers 提出基于PatchMatch和Transformers的动态纹理转移方法 VQ-VAE

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

#题目一句话要点标签🔗⭐
16 VIS-MAE: An Efficient Self-supervised Learning Approach on Medical Image Segmentation and Classification 提出VIS-MAE以解决医学图像分割与分类中的数据效率问题 masked autoencoder MAE foundation model ✅
17 Dual-Student Knowledge Distillation Networks for Unsupervised Anomaly Detection 提出双学生知识蒸馏网络以解决无监督异常检测问题 distillation
18 Lightweight Pixel Difference Networks for Efficient Visual Representation Learning 提出轻量级像素差异网络以解决视觉表示学习的效率问题 representation learning ✅

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

#题目一句话要点标签🔗⭐
19 Self-supervised learning of video representations from a child's perspective 提出自监督学习方法以从儿童视角学习视频表征 egocentric

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
20 FineBio: A Fine-Grained Video Dataset of Biological Experiments with Hierarchical Annotation 提出FineBio数据集以解决生物实验视频理解问题 manipulation ✅

⬅️ 返回 cs.CV 首页 · 🏠 返回主页