cs.CV(2025-12-01)

📊 共 9 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) (2 🔗1) 支柱一:机器人控制 (Robot Control) (2) 支柱六:视频提取与匹配 (Video Extraction) (2) 支柱三:空间感知 (Perception & SLAM) (2 🔗1) 支柱三:空间感知与语义 (Perception & Semantics) (1)

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

#题目一句话要点标签🔗
1 GrndCtrl: Grounding World Models via Self-Supervised Reward Alignment GrndCtrl:通过自监督奖励对齐实现世界模型的几何化,提升导航稳定性 reinforcement learning world model large language model
2 Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching 提出基于流匹配的点云配准方法,提升低重叠度场景下的配准精度。 flow matching

🔬 支柱一:机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗
3 SPARK: Sim-ready Part-level Articulated Reconstruction with VLM Knowledge SPARK:利用VLM知识进行可用于仿真的部件级铰接重建 manipulation scene understanding embodied AI
4 M4-BLIP: Advancing Multi-Modal Media Manipulation Detection through Face-Enhanced Local Analysis M4-BLIP:通过人脸增强的局部分析提升多模态媒体篡改检测 manipulation

🔬 支柱六:视频提取与匹配 (Video Extraction) (2 篇)

#题目一句话要点标签🔗
5 Visual Sync: Multi-Camera Synchronization via Cross-View Object Motion VisualSync:通过跨视角物体运动实现多相机视频同步 feature matching
6 StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos StreamGaze:提出基于注视引导的流视频时序推理与主动理解评测基准。 egocentric

🔬 支柱三:空间感知 (Perception & SLAM) (2 篇)

#题目一句话要点标签🔗
7 VSRD++: Autolabeling for 3D Object Detection via Instance-Aware Volumetric Silhouette Rendering 提出VSRD++以解决单目3D物体检测中的标注依赖问题 scene understanding point cloud
8 S$^2$-MLLM: Boosting Spatial Reasoning Capability of MLLMs for 3D Visual Grounding with Structural Guidance S$^2$-MLLM:通过结构引导增强MLLM在3D视觉定位中的空间推理能力 point cloud

🔬 支柱三:空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗
9 SplatSuRe: Selective Super-Resolution for Multi-view Consistent 3D Gaussian Splatting SplatSuRe:针对多视角一致性3D高斯溅射的选择性超分辨率方法 3D gaussian splatting 3DGS gaussian splatting

⬅️ 返回 cs.CV 首页 · 🏠 返回主页