cs.CV(2025-02-28)

📊 共 8 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

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

🔬 支柱二:RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗
1 WorldModelBench: Judging Video Generation Models As World Models 提出WorldModelBench,用于评估视频生成模型作为世界模型的性能,尤其关注物理规律遵循。 world model instruction following
2 STPro: Spatial and Temporal Progressive Learning for Weakly Supervised Spatio-Temporal Grounding STPro:时空渐进学习框架,用于弱监督时空视频定位 curriculum learning foundation model
3 Dataset Distillation with Neural Characteristic Function: A Minmax Perspective 提出神经特征函数以解决数据集蒸馏中的分布匹配问题 distillation

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

#题目一句话要点标签🔗
4 EndoPBR: Material and Lighting Estimation for Photorealistic Surgical Simulations via Physically-based Rendering EndoPBR:通过物理渲染进行逼真手术模拟的材质和光照估计 depth estimation 3D gaussian splatting gaussian splatting
5 RTGen: Real-Time Generative Detection Transformer 提出RTGen:一种实时生成式检测Transformer,解决开放词汇目标检测的速度瓶颈。 open-vocabulary open vocabulary

🔬 支柱一:机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗
6 Towards General Visual-Linguistic Face Forgery Detection(V2) 提出FFTG,通过伪造掩码和提示策略提升视觉-语言人脸伪造检测的准确性。 manipulation large language model multimodal

🔬 支柱六:视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗
7 EDM: Equirectangular Projection-Oriented Dense Kernelized Feature Matching 提出EDM,一种面向全景图像的密集核化特征匹配算法,显著提升匹配精度。 feature matching

🔬 支柱九:具身大模型 (Embodied Foundation Models) (1 篇)

#题目一句话要点标签🔗
8 SciceVPR: Stable Cross-Image Correlation Enhanced Model for Visual Place Recognition SciceVPR:稳定跨图像相关增强的视觉定位模型 foundation model

⬅️ 返回 cs.CV 首页 · 🏠 返回主页