cs.CV（2024-02-03）

📊 共 17 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (6 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗1) 支柱一：机器人控制 (Robot Control) (2) 支柱八：物理动画 (Physics-based Animation) (1) 支柱九：具身大模型 (Embodied Foundation Models) (1 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (6 篇)

#题目一句话要点标签🔗⭐
1 RIDERS: Radar-Infrared Depth Estimation for Robust Sensing 提出雷达-红外深度估计方法以解决恶劣天气下的感知问题 depth estimation monocular depth metric depth ✅
2 Polyp-DAM: Polyp segmentation via depth anything model 提出深度任意模型以解决息肉分割问题 Depth Anything ✅
3 NeuV-SLAM: Fast Neural Multiresolution Voxel Optimization for RGBD Dense SLAM 提出NeuV-SLAM以解决RGBD密集SLAM的快速收敛问题 implicit representation scene reconstruction
4 Implicit Neural Representation of Tileable Material Textures 提出隐式神经网络表示可平铺材质纹理以解决高分辨率重建问题 implicit representation
5 UMCFuse: A Unified Multiple Complex Scenes Infrared and Visible Image Fusion Framework 提出UMCFuse以解决复杂场景下红外与可见光图像融合问题 depth estimation ✅
6 All-weather Multi-Modality Image Fusion: Unified Framework and 100k Benchmark 提出统一的全天气多模态图像融合模型以解决天气干扰问题 depth estimation ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
7 Multi-RoI Human Mesh Recovery with Camera Consistency and Contrastive Losses 提出多RoI人类网格恢复方法以解决相机一致性问题 contrastive learning human mesh recovery HMR ✅
8 MLIP: Enhancing Medical Visual Representation with Divergence Encoder and Knowledge-guided Contrastive Learning 提出MLIP框架以解决医学视觉表征的多粒度学习问题 representation learning contrastive learning multimodal
9 MSPM: A Multi-Site Physiological Monitoring Dataset for Remote Pulse, Respiration, and Blood Pressure Estimation 提出MSPM数据集以支持多部位生理监测的研究 MAE PULSE
10 Attention-Mamba: A Mamba-Enhanced Multi-Scale Parallel Inference Network for Medical Image Segmentation 提出Attention-Mamba以解决医学图像分割中的多尺度特征提取问题 Mamba state space model
11 Precise Knowledge Transfer via Flow Matching 提出FM-KT框架以实现精确知识转移 flow matching distillation
12 Wavelet-Decoupling Contrastive Enhancement Network for Fine-Grained Skeleton-Based Action Recognition 提出波形解耦对比增强网络以解决细粒度骨架动作识别问题 contrastive learning spatiotemporal

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
13 S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation 提出S-NeRF++以解决传统自动驾驶仿真系统的局限性 manipulation NeRF neural radiance field
14 Digital Video Manipulation Detection Technique Based on Compression Algorithms 基于压缩算法提出视频篡改检测技术 manipulation

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

#题目一句话要点标签🔗⭐
15 BVI-Lowlight: Fully Registered Benchmark Dataset for Low-Light Video Enhancement 提出BVI-Lowlight数据集以解决低光视频增强问题 spatiotemporal

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

#题目一句话要点标签🔗⭐
16 Multimodal-Enhanced Objectness Learner for Corner Case Detection in Autonomous Driving 提出多模态增强物体性学习器以解决自动驾驶中的角落案例检测问题 multimodal ✅

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

#题目一句话要点标签🔗⭐
17 Data-Driven Prediction of Seismic Intensity Distributions Featuring Hybrid Classification-Regression Models 提出混合分类回归模型以预测地震强度分布 motion prediction

⬅️ 返回 cs.CV 首页 · 🏠 返回主页