cs.CV（2024-01-17）

📊 共 15 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 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗2) 支柱五：交互与反应 (Interaction & Reaction) (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	OCTO+: A Suite for Automatic Open-Vocabulary Object Placement in Mixed Reality	提出OCTO+以解决增强现实中开放词汇物体放置问题	open-vocabulary open vocabulary Octo
2	SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding	提出SceneVerse以解决3D视觉语言对齐问题	scene understanding visual grounding zero-shot transfer
3	POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images	提出POP-3D以解决开放词汇3D占用预测问题	open-vocabulary open vocabulary	✅
4	IPR-NeRF: Ownership Verification meets Neural Radiance Field	提出IPR-NeRF框架以解决NeRF模型的知识产权保护问题	NeRF neural radiance field
5	Event-Based Visual Odometry on Non-Holonomic Ground Vehicles	提出基于事件的视觉里程计以解决非完整地面车辆的运动估计问题	visual odometry motion estimation	✅
6	ICON: Incremental CONfidence for Joint Pose and Radiance Field Optimization	提出ICON以解决NeRF训练中的姿态初始化问题	NeRF neural radiance field
7	GARField: Group Anything with Radiance Fields	提出GARField以解决3D场景分组模糊性问题	scene understanding

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

#	题目	一句话要点	标签	🔗	⭐
8	Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model	提出Vim以解决视觉表示学习中的计算与内存效率问题	Mamba SSM state space model	✅
9	TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusion	提出TextureDreamer以解决纹理合成的挑战	dreamer distillation
10	CrossVideo: Self-supervised Cross-modal Contrastive Learning for Point Cloud Video Understanding	提出CrossVideo以解决点云视频理解中的自监督学习问题	contrastive learning
11	Hearing Loss Detection from Facial Expressions in One-on-one Conversations	提出基于面部表情的听力损失检测方法以解决沟通困难问题	representation learning egocentric

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

#	题目	一句话要点	标签	🔗	⭐
12	Vlogger: Make Your Dream A Vlog	提出Vlogger以解决复杂视频生成问题	large language model foundation model	✅
13	Remote Sensing ChatGPT: Solving Remote Sensing Tasks with ChatGPT and Visual Models	提出Remote Sensing ChatGPT以解决遥感任务的自动化问题	large language model foundation model	✅
14	COCO is "ALL'' You Need for Visual Instruction Fine-tuning	提出基于COCO数据集的新视觉指令微调方法以提升多轮对话性能	large language model instruction following

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
15	MedBlindTuner: Towards Privacy-preserving Fine-tuning on Biomedical Images with Transformers and Fully Homomorphic Encryption	提出MedBlindTuner以解决医疗图像隐私保护问题	OMOMO

⬅️ 返回 cs.CV 首页 · 🏠 返回主页