cs.CV（2025-11-16）

📊 共 12 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱三：空间感知 (Perception & SLAM) (8 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱三：空间感知 (Perception & SLAM) (8 篇)

#题目一句话要点标签🔗⭐
1 DPVO-QAT++: Heterogeneous QAT and CUDA Kernel Fusion for High-Performance Deep Patch Visual Odometry DPVO-QAT++：异构量化感知训练与CUDA核融合，提升深度Patch视觉里程计性能。 visual odometry visual SLAM SLAM
2 OPFormer: Object Pose Estimation leveraging foundation model with geometric encoding OPFormer：利用几何编码和基础模型进行物体姿态估计 NeRF pose estimation
3 Deep Imbalanced Multi-Target Regression: 3D Point Cloud Voxel Content Estimation in Simulated Forests 提出基于KPConv的深度不平衡多目标回归方法，用于模拟森林中三维点云体素内容估计。 point cloud
4 Appreciate the View: A Task-Aware Evaluation Framework for Novel View Synthesis 提出任务感知的新视角合成评估框架，解决现有指标与人类感知不一致问题 novel view synthesis
5 Toward Real-world Text Image Forgery Localization: Structured and Interpretable Data Synthesis 提出基于傅里叶级数的篡改合成方法以解决文本图像篡改定位问题 localization ✅
6 BridgeEQA: Virtual Embodied Agents for Real Bridge Inspections 提出BridgeEQA桥梁检测基准与EMVR模型，解决具身环境问答中的多尺度推理难题。 navigation
7 C3Net: Context-Contrast Network for Camouflaged Object Detection C3Net：上下文对比网络用于伪装目标检测，显著提升检测精度。 localization ✅
8 Visible Structure Retrieval for Lightweight Image-Based Relocalisation 提出可见结构检索网络，实现轻量级图像重定位 pose estimation

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

#题目一句话要点标签🔗⭐
9 DensePercept-NCSSD: Vision Mamba towards Real-time Dense Visual Perception with Non-Causal State Space Duality 提出DensePercept-NCSSD，利用非因果选择性状态空间Mamba实现实时稠密视觉感知。 Mamba disparity estimation optical flow ✅
10 X-VMamba: Explainable Vision Mamba X-VMamba：基于可控性的Vision Mamba可解释性框架，应用于医学影像 Mamba SSM state space model
11 MOON2.0: Dynamic Modality-balanced Multimodal Representation Learning for E-commerce Product Understanding 提出MOON2.0以解决电商产品理解中的多模态不平衡问题 representation learning

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
12 HiGFA: Hierarchical Guidance for Fine-grained Data Augmentation with Diffusion Models HiGFA：利用扩散模型和分层引导进行细粒度数据增强 classifier-free guidance

⬅️ 返回 cs.CV 首页 · 🏠 返回主页