cs.CV（2023-11-10）

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

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

#	题目	一句话要点	标签	🔗	⭐
1	A Neural Height-Map Approach for the Binocular Photometric Stereo Problem	提出神经高度图方法以解决双目光度立体问题	NeRF height map
2	Semantic Map Guided Synthesis of Wireless Capsule Endoscopy Images using Diffusion Models	提出基于扩散模型的语义地图引导无线胶囊内窥镜图像合成方法	semantic map
3	Automatic extraction and 3D reconstruction of split wire from point cloud data based on improved DPC algorithm	提出改进DPC算法以实现点云数据的自动分割与3D重建	3D reconstruction
4	UMedNeRF: Uncertainty-aware Single View Volumetric Rendering for Medical Neural Radiance Fields	提出UMedNeRF以解决CT成像中辐射剂量过高的问题	neural radiance field
5	ASSIST: Interactive Scene Nodes for Scalable and Realistic Indoor Simulation	提出ASSIST以解决室内场景交互与真实感模拟问题	neural radiance field

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

#	题目	一句话要点	标签	🔗	⭐
6	MonoProb: Self-Supervised Monocular Depth Estimation with Interpretable Uncertainty	提出MonoProb以解决单目深度估计的不确定性问题	distillation depth estimation monocular depth	✅
7	Learning Contrastive Self-Distillation for Ultra-Fine-Grained Visual Categorization Targeting Limited Samples	提出CSDNet以解决超细粒度视觉分类中的样本不足问题	contrastive learning distillation

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

#	题目	一句话要点	标签	🔗	⭐
8	Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks	提出Florence-2以解决多任务视觉模型的复杂性问题	foundation model
9	Watermarking Vision-Language Pre-trained Models for Multi-modal Embedding as a Service	提出VLPMarker以解决多模态EaaS中的版权保护问题	large language model	✅

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

#	题目	一句话要点	标签	🔗	⭐
10	Towards A Unified Neural Architecture for Visual Recognition and Reasoning	提出统一神经架构以解决视觉识别与推理问题	spatiotemporal

⬅️ 返回 cs.CV 首页 · 🏠 返回主页