cs.CV（2023-11-01）

📊 共 11 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) (4 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (4 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Single-view 3D Scene Reconstruction with High-fidelity Shape and Texture	提出单视图神经隐式形状与辐射场以解决3D场景重建问题	3D reconstruction scene reconstruction scene understanding
2	ChatGPT-Powered Hierarchical Comparisons for Image Classification	提出层次比较框架以解决图像分类中的零-shot开放词汇挑战	open-vocabulary open vocabulary large language model
3	Event-based Background-Oriented Schlieren	提出基于事件的背景导向施莱伦成像以解决传统方法的局限性	optical flow	✅
4	LatentWarp: Consistent Diffusion Latents for Zero-Shot Video-to-Video Translation	提出LatentWarp以解决视频生成中的时间一致性问题	optical flow

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

#	题目	一句话要点	标签	🔗	⭐
5	CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders	提出CROMA框架以提升遥感数据的自监督学习效果	masked autoencoder contrastive learning multimodal
6	Rethinking Samples Selection for Contrastive Learning: Mining of Potential Samples	提出潜在样本挖掘方法以优化对比学习	contrastive learning
7	Graph Representation Learning for Infrared and Visible Image Fusion	提出图表示学习方法以解决红外与可见光图像融合问题	representation learning
8	TPSeNCE: Towards Artifact-Free Realistic Rain Generation for Deraining and Object Detection in Rain	提出TPSeNCE以解决雨天图像生成中的伪影问题	contrastive learning scene understanding	✅

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

#	题目	一句话要点	标签	🔗	⭐
9	ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab	提出ProBio数据集以解决分子生物学实验可重复性问题	multimodal
10	Sounding Bodies: Modeling 3D Spatial Sound of Humans Using Body Pose and Audio	提出3D空间音频模型以解决人类身体声音建模不足问题	multimodal

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
11	Beyond still images: Temporal features and input variance resilience	提出基于视频的视觉理解模型以提升输入变化的鲁棒性	spatiotemporal

⬅️ 返回 cs.CV 首页 · 🏠 返回主页