cs.CV（2024-04-09）

📊 共 26 篇论文 | 🔗 8 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (15 🔗4) 支柱九：具身大模型 (Embodied Foundation Models) (4 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗2) 支柱一：机器人控制 (Robot Control) (2 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (15 篇)

#题目一句话要点标签🔗⭐
1 Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection 提出CMD-SE框架以解决开放词汇HOI检测问题 open-vocabulary open vocabulary human-object interaction ✅
2 Gaussian Pancakes: Geometrically-Regularized 3D Gaussian Splatting for Realistic Endoscopic Reconstruction 提出Gaussian Pancakes以解决内窥镜3D重建问题 3D gaussian splatting 3D reconstruction gaussian splatting
3 3D Geometry-aware Deformable Gaussian Splatting for Dynamic View Synthesis 提出3D几何感知可变形高斯点云以解决动态视图合成问题 3D gaussian splatting gaussian splatting splatting ✅
4 Revising Densification in Gaussian Splatting 提出基于像素误差的新密度控制方法以改善3D高斯点云表现 3D gaussian splatting 3DGS gaussian splatting
5 Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generation 提出FreeDA以解决开放词汇语义分割问题 open-vocabulary open vocabulary multimodal
6 HFNeRF: Learning Human Biomechanic Features with Neural Radiance Fields 提出HFNeRF以解决人类生物力学特征生成问题 NeRF neural radiance field foundation model
7 End-to-End Rate-Distortion Optimized 3D Gaussian Representation 提出RDO-Gaussian以解决3D Gaussian表示的存储问题 3D gaussian splatting 3DGS gaussian splatting
8 GHNeRF: Learning Generalizable Human Features with Efficient Neural Radiance Fields 提出GHNeRF以解决人类姿态与结构信息缺失问题 NeRF neural radiance field
9 QueSTMaps: Queryable Semantic Topological Maps for 3D Scene Understanding 提出QueSTMaps以解决3D场景理解中的拓扑区域识别问题 scene understanding
10 Hash3D: Training-free Acceleration for 3D Generation 提出Hash3D以解决3D生成效率低下问题 3D gaussian splatting gaussian splatting splatting ✅
11 Incremental Joint Learning of Depth, Pose and Implicit Scene Representation on Monocular Camera in Large-scale Scenes 提出增量联合学习框架以解决大规模场景的深度、姿态与隐式场景表示问题 depth estimation scene reconstruction
12 RoadBEV: Road Surface Reconstruction in Bird's Eye View 提出RoadBEV以解决道路表面重建问题 depth estimation monocular depth ✅
13 DaF-BEVSeg: Distortion-aware Fisheye Camera based Bird's Eye View Segmentation with Occlusion Reasoning 提出DaF-BEVSeg以解决鱼眼相机的鸟瞰视图分割问题 scene understanding
14 Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences 提出MicKey以解决2D图像间的度量相对姿态估计问题 scene reconstruction
15 Enhanced Radar Perception via Multi-Task Learning: Towards Refined Data for Sensor Fusion Applications 通过多任务学习提升雷达感知以解决传感器融合问题 depth estimation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
16 Playing to Vision Foundation Model's Strengths in Stereo Matching 提出ViTAS以解决立体匹配中的几何视觉挑战 foundation model
17 WebCode2M: A Real-World Dataset for Code Generation from Webpage Designs 提出WebCode2M数据集以解决网页设计代码生成问题 large language model multimodal
18 OmniFusion Technical Report 提出OmniFusion以提升多模态视觉与语言任务的性能 large language model multimodal ✅
19 Learning Embeddings with Centroid Triplet Loss for Object Identification in Robotic Grasping 提出中心三元组损失以解决机器人抓取中的物体识别问题 foundation model

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

#题目一句话要点标签🔗⭐
20 MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection 提出MambaAD以解决多类无监督异常检测问题 Mamba SSM state space model ✅
21 RhythmMamba: Fast, Lightweight, and Accurate Remote Physiological Measurement 提出RhythmMamba以解决远程生理测量中的时序依赖与冗余问题 Mamba state space model spatiotemporal ✅
22 Robust feature knowledge distillation for enhanced performance of lightweight crack segmentation models 提出鲁棒特征知识蒸馏以提升轻量裂缝分割模型性能 distillation

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
23 Raster Forge: Interactive Raster Manipulation Library and GUI for Python 提出Raster Forge以解决遥感数据处理与分析问题 manipulation
24 EasyTrack: Efficient and Compact One-stream 3D Point Clouds Tracker 提出EasyTrack以解决3D点云单目标跟踪效率低的问题 motion tracking ✅

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

#题目一句话要点标签🔗⭐
25 Space-Time Video Super-resolution with Neural Operator 提出基于神经算子的时空视频超分辨率方法以解决运动估计问题 motion estimation spatiotemporal

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
26 Spatial-Temporal Multi-level Association for Video Object Segmentation 提出空间-时间多级关联框架以解决视频目标分割问题 feature matching

⬅️ 返回 cs.CV 首页 · 🏠 返回主页