cs.CV（2023-10-11）

📊 共 14 篇论文 | 🔗 7 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (7 🔗2) 支柱四：生成式动作 (Generative Motion) (2 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (2 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1) 支柱六：视频提取与匹配 (Video Extraction) (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 Ferret: Refer and Ground Anything Anywhere at Any Granularity 提出Ferret以解决多模态图像理解中的空间引用与定位问题 open-vocabulary open vocabulary large language model ✅
2 rpcPRF: Generalizable MPI Neural Radiance Field for Satellite Camera 提出rpcPRF以解决卫星图像新视角合成问题 NeRF neural radiance field implicit representation
3 Dynamic Appearance Particle Neural Radiance Field 提出动态外观粒子神经辐射场以解决动态场景建模问题 NeRF neural radiance field ✅
4 Echocardiography video synthesis from end diastolic semantic map via diffusion model 提出基于扩散模型的心脏超声视频合成方法以解决数据集不足问题 semantic map
5 PoRF: Pose Residual Field for Accurate Neural Surface Reconstruction 提出Pose Residual Field以解决神经表面重建中的姿态噪声问题 NeRF implicit representation
6 DESTINE: Dynamic Goal Queries with Temporal Transductive Alignment for Trajectory Prediction 提出DESTINE以解决多智能体轨迹预测中的动态目标查询问题 semantic map
7 S4C: Self-Supervised Semantic Scene Completion with Neural Fields 提出S4C以解决自监督语义场景补全问题 scene understanding

🔬 支柱四：生成式动作 (Generative Motion) (2 篇)

#题目一句话要点标签🔗⭐
8 Guided Attention for Interpretable Motion Captioning 提出引导注意力机制以提升可解释的人体动作字幕生成 motion generation human motion human motion generation ✅
9 DeepSimHO: Stable Pose Estimation for Hand-Object Interaction via Physics Simulation 提出DeepSimHO以解决手-物体交互中的姿态估计不稳定问题 penetration ✅

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗⭐
10 Uni-paint: A Unified Framework for Multimodal Image Inpainting with Pretrained Diffusion Model 提出Uni-paint以解决多模态图像修复控制不足的问题 multimodal ✅
11 VeCLIP: Improving CLIP Training via Visual-enriched Captions 提出VeCLIP以解决图像文本对齐中的噪声问题 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
12 Heuristic Vision Pre-Training with Self-Supervised and Supervised Multi-Task Learning 提出一种多任务学习框架以提升视觉模型的预训练效果 representation learning contrastive learning foundation model
13 A Discrepancy Aware Framework for Robust Anomaly Detection 提出一种差异感知框架以解决缺陷检测的鲁棒性问题 teacher-student distillation ✅

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

#题目一句话要点标签🔗⭐
14 LangNav: Language as a Perceptual Representation for Navigation 提出LangNav以解决低数据环境下的视觉语言导航问题 egocentric VLN

⬅️ 返回 cs.CV 首页 · 🏠 返回主页