cs.CV（2025-11-05）
📊 共 10 篇论文 | 🔗 2 篇有代码
🎯 兴趣领域导航
支柱三：空间感知 (Perception & SLAM) (5 🔗2)
支柱二：RL算法与架构 (RL & Architecture) (1)
支柱五：交互与反应 (Interaction & Reaction) (1)
支柱六：视频提取与匹配 (Video Extraction & Matching) (1)
支柱四：生成式动作 (Generative Motion) (1)
支柱八：物理动画 (Physics-based Animation) (1)
🔬 支柱三：空间感知 (Perception & SLAM) (5 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | DentalSplat: Dental Occlusion Novel View Synthesis from Sparse Intra-Oral Photographs | 提出DentalSplat以解决稀疏口腔影像下的牙齿咬合重建问题 | 3D gaussian splatting 3DGS gaussian splatting | ||
| 2 | SurgViVQA: Temporally-Grounded Video Question Answering for Surgical Scene Understanding | SurgViVQA：面向手术场景理解的时序视频问答模型 | scene understanding | ✅ | |
| 3 | IEC3D-AD: A 3D Dataset of Industrial Equipment Components for Unsupervised Point Cloud Anomaly Detection | 提出IEC3D-AD工业零件3D异常检测数据集及GMANet异常检测方法 | point cloud | ||
| 4 | Subsampled Randomized Fourier GaLore for Adapting Foundation Models in Depth-Driven Liver Landmark Segmentation | 提出SRFT-GaLore，用于深度驱动的肝脏地标分割中高效自适应基础模型。 | monocular depth localization Depth Anything | ||
| 5 | Beyond Softmax: Dual-Branch Sigmoid Architecture for Accurate Class Activation Maps | 提出双分支Sigmoid架构，解决CAM中logit偏移和符号坍塌问题，提升定位精度。 | localization | ✅ |
🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 6 | Investigating Robot Control Policy Learning for Autonomous X-ray-guided Spine Procedures | 提出基于模仿学习的机器人控制策略，用于X射线引导的脊柱手术 | policy learning imitation learning navigation |
🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 7 | Part-Aware Bottom-Up Group Reasoning for Fine-Grained Social Interaction Detection | 提出Part-Aware自底向上群体推理框架，用于细粒度社交互动检测 | social interaction |
🔬 支柱六：视频提取与匹配 (Video Extraction & Matching) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 8 | Human Mesh Modeling for Anny Body | 提出Anny：一个基于人体测量学知识的可微、无扫描的人体网格建模方法 | human mesh recovery HMR |
🔬 支柱四：生成式动作 (Generative Motion) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 9 | UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions | UniAVGen：提出一种非对称跨模态交互的统一音视频生成框架 | classifier-free guidance |
🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 10 | Computed Tomography (CT)-derived Cardiovascular Flow Estimation Using Physics-Informed Neural Networks Improves with Sinogram-based Training: A Simulation Study | 提出SinoFlow：利用Sinogram数据训练的物理信息神经网络提升CT血流估计精度 | PULSE |