cs.CV（2024-03-02）

📊 共 10 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (5 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱七：动作重定向 (Motion Retargeting) (2)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
1	NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning	提出NeRF-VPT以解决新视角合成中的图像质量问题	NeRF neural radiance field	✅
2	Neural radiance fields-based holography [Invited]	提出基于神经辐射场的全息图生成方法以解决3D数据计算难题	NeRF neural radiance field
3	Benchmarking Segmentation Models with Mask-Preserved Attribute Editing	提出掩膜保留属性编辑方法以评估分割模型的鲁棒性	open-vocabulary open vocabulary	✅
4	Neural Field Classifiers via Target Encoding and Classification Loss	提出神经场分类器以解决回归模型的局限性	NeRF neural radiance field
5	Depth Information Assisted Collaborative Mutual Promotion Network for Single Image Dehazing	提出深度信息辅助的协同互促网络以解决单幅图像去雾问题	depth estimation

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

#	题目	一句话要点	标签	🔗	⭐
6	Adversarial Testing for Visual Grounding via Image-Aware Property Reduction	提出PEELING以解决视觉定位模型的对抗测试问题	multimodal visual grounding
7	REWIND Dataset: Privacy-preserving Speaking Status Segmentation from Multimodal Body Movement Signals in the Wild	提出REWIND数据集以解决无音频场景下的说话状态识别问题	multimodal
8	Data-free Multi-label Image Recognition via LLM-powered Prompt Tuning	提出无数据多标签图像识别框架以解决数据依赖问题	large language model

🔬 支柱七：动作重定向 (Motion Retargeting) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
9	Consistent and Optimal Solution to Camera Motion Estimation	提出一致且最优的相机运动估计解决方案	motion estimation
10	SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code	提出SceneCraft以解决3D场景合成问题	spatial relationship large language model foundation model

⬅️ 返回 cs.CV 首页 · 🏠 返回主页