cs.CV（2023-10-15）

📊 共 12 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (3 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (2 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱六：视频提取与匹配 (Video Extraction) (2 🔗1) 支柱一：机器人控制 (Robot Control) (2 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	Can GPT-4V(ision) Serve Medical Applications? Case Studies on GPT-4V for Multimodal Medical Diagnosis	评估GPT-4V在多模态医学诊断中的应用潜力	foundation model multimodal	✅
2	New Benchmarks for Asian Facial Recognition Tasks: Face Classification with Large Foundation Models	提出KoIn数据集以提升亚洲人脸识别分类性能	foundation model	✅
3	Beyond Segmentation: Road Network Generation with Multi-Modal LLMs	提出多模态大语言模型以解决道路网络生成问题	large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
4	CBARF: Cascaded Bundle-Adjusting Neural Radiance Fields from Imperfect Camera Poses	提出CBARF以解决不完美相机姿态下的3D重建问题	3D reconstruction NeRF neural radiance field
5	AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimation	提出AugUndo以解决单目深度补全与估计中的数据增强问题	monocular depth	✅

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

#	题目	一句话要点	标签	🔗	⭐
6	ProteusNeRF: Fast Lightweight NeRF Editing using 3D-Aware Image Context	提出ProteusNeRF以解决NeRF交互编辑效率低的问题	distillation NeRF neural radiance field
7	Top-K Pooling with Patch Contrastive Learning for Weakly-Supervised Semantic Segmentation	提出Top-K池化与补丁对比学习以解决弱监督语义分割问题	contrastive learning

🔬 支柱六：视频提取与匹配 (Video Extraction) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
8	Zero-Shot Object Goal Visual Navigation With Class-Independent Relationship Network	提出类独立关系网络以解决零样本目标视觉导航问题	egocentric	✅
9	OAAFormer: Robust and Efficient Point Cloud Registration Through Overlapping-Aware Attention in Transformer	提出OAAFormer以解决点云配准中的对应关系质量问题	feature matching

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
10	AEP$n$P: A Less-constrained EP$n$P Solver for Pose Estimation with Anisotropic Scaling	提出AEP$n$P以解决物体姿态估计中的约束问题	manipulation	✅
11	Unsupervised Discovery of Interpretable Directions in h-space of Pre-trained Diffusion Models	提出无监督学习方法以发现预训练扩散模型中的可解释方向	manipulation

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

#	题目	一句话要点	标签	🔗	⭐
12	MoEmo Vision Transformer: Integrating Cross-Attention and Movement Vectors in 3D Pose Estimation for HRI Emotion Detection	提出MoEmo Vision Transformer以解决人机交互中的情感检测问题	motion estimation

⬅️ 返回 cs.CV 首页 · 🏠 返回主页