cs.CV(2025-12-13)

📊 共 10 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱三:空间感知 (Perception & SLAM) (6) 支柱一:机器人控制 (Robot Control) (2) 支柱七:动作重定向 (Motion Retargeting) (1 🔗1) 支柱八:物理动画 (Physics-based Animation) (1)

🔬 支柱三:空间感知 (Perception & SLAM) (6 篇)

#题目一句话要点标签🔗
1 BokehDepth: Enhancing Monocular Depth Estimation through Bokeh Generation 提出BokehDepth,利用散焦作为辅助几何线索,提升单目深度估计的精度和鲁棒性。 depth estimation monocular depth metric depth
2 Audio-Visual Camera Pose Estimation with Passive Scene Sounds and In-the-Wild Video 提出一种音视频融合的相机位姿估计方法,利用场景声音增强视觉信息,提升野外视频的鲁棒性。 scene understanding pose estimation
3 MRD: Using Physically Based Differentiable Rendering to Probe Vision Models for 3D Scene Understanding 提出MRD,利用可微渲染探究视觉模型对3D场景的理解能力 scene understanding
4 A Graph Attention Network-Based Framework for Reconstructing Missing LiDAR Beams 提出基于图注意力网络的LiDAR缺失波束重建框架,提升自动驾驶环境感知能力。 point cloud
5 A Multi-Year Urban Streetlight Imagery Dataset for Visual Monitoring and Spatio-Temporal Drift Detection 发布城市街道照明多年度图像数据集,用于视觉监控和时空漂移检测。 scene understanding
6 SMRABooth: Subject and Motion Representation Alignment for Customized Video Generation SMRABooth:通过主体与运动表征对齐实现定制化视频生成 optical flow

🔬 支柱一:机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗
7 Speedrunning ImageNet Diffusion 提出SR-DiT,通过集成多种优化策略加速ImageNet扩散模型训练。 running classifier-free guidance
8 A Hybrid Deep Learning Framework for Emotion Recognition in Children with Autism During NAO Robot-Mediated Interaction 提出一种混合深度学习框架,用于识别自闭症儿童在NAO机器人交互中的情绪。 humanoid humanoid robot social interaction

🔬 支柱七:动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗
9 Endless World: Real-Time 3D-Aware Long Video Generation Endless World:实时3D感知无限长视频生成框架 geometric consistency

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

#题目一句话要点标签🔗
10 ALERT Open Dataset and Input-Size-Agnostic Vision Transformer for Driver Activity Recognition using IR-UWB 提出ISA-ViT和ALERT数据集,用于解决基于IR-UWB雷达的驾驶员行为识别问题 PULSE

⬅️ 返回 cs.CV 首页 · 🏠 返回主页