cs.CV（2024-04-11）

📊 共 25 篇论文 | 🔗 7 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (9 🔗3) 支柱三：空间感知与语义 (Perception & Semantics) (7 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (6 🔗2) 支柱一：机器人控制 (Robot Control) (2) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗⭐
1 Connecting NeRFs, Images, and Text 提出多模态框架以连接NeRF、图像与文本 representation learning NeRF neural radiance field
2 Boosting Self-Supervision for Single-View Scene Completion via Knowledge Distillation 提出MVBTS以提升单视图场景补全的自监督学习效果 distillation NeRF neural radiance field
3 FusionMamba: Efficient Remote Sensing Image Fusion with State Space Model 提出FusionMamba以解决遥感图像融合效率问题 Mamba SSM state space model ✅
4 DGMamba: Domain Generalization via Generalized State Space Model 提出DGMamba以解决领域泛化问题 Mamba SSM state space model ✅
5 Depth Estimation using Weighted-loss and Transfer Learning 提出加权损失与迁移学习以提升深度估计精度 MAE depth estimation scene understanding
6 SurvMamba: State Space Model with Multi-grained Multi-modal Interaction for Survival Prediction 提出SurvMamba以解决生存预测中的多模态融合问题 Mamba state space model
7 Simba: Mamba augmented U-ShiftGCN for Skeletal Action Recognition in Videos 提出Simba框架以提升视频中的骨骼动作识别性能 Mamba state space model
8 Self-supervised Dataset Distillation: A Good Compression Is All You Need 提出自监督压缩框架SC-DD以优化数据集蒸馏 distillation ✅
9 GLID: Pre-training a Generalist Encoder-Decoder Vision Model 提出GLID以解决计算机视觉任务中的架构一致性问题 masked autoencoder depth estimation

🔬 支柱三：空间感知与语义 (Perception & Semantics) (7 篇)

#题目一句话要点标签🔗⭐
10 Transferable and Principled Efficiency for Open-Vocabulary Segmentation 提出可转移且原则性高的高效开放词汇分割方法 open-vocabulary open vocabulary foundation model ✅
11 SciFlow: Empowering Lightweight Optical Flow Models with Self-Cleaning Iterations 提出SciFlow以解决实时光流估计中的模糊性问题 optical flow
12 Stereo-LiDAR Depth Estimation with Deformable Propagation and Learned Disparity-Depth Conversion 提出SDG-Depth以解决立体相机与LiDAR深度估计问题 depth estimation ✅
13 G-NeRF: Geometry-enhanced Novel View Synthesis from Single-View Images 提出G-NeRF以解决单视图图像的几何增强新视图合成问题 NeRF
14 GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh 提出GoMAvatar以解决单目视频人类建模效率低的问题 gaussian splatting splatting
15 Chaos in Motion: Unveiling Robustness in Remote Heart Rate Measurement through Brain-Inspired Skin Tracking 提出HR-RST以解决远程心率测量中的隐私与准确性问题 optical flow spatiotemporal
16 Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange 提出对象交换策略以解决点云自监督学习中的依赖问题 scene understanding

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#题目一句话要点标签🔗⭐
17 CopilotCAD: Empowering Radiologists with Report Completion Models and Quantitative Evidence from Medical Image Foundation Models 提出CopilotCAD以增强放射科医师的报告生成能力 large language model foundation model
18 Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models 提出Ferret-v2以解决现有视觉编码能力不足的问题 large language model
19 Streamlined Photoacoustic Image Processing with Foundation Models: A Training-Free Solution 提出基于基础模型的无训练光声图像分割方法 foundation model
20 Any2Point: Empowering Any-modality Large Models for Efficient 3D Understanding 提出Any2Point以解决多模态大模型在3D理解中的效率问题 foundation model ✅
21 Heron-Bench: A Benchmark for Evaluating Vision Language Models in Japanese 提出Japanese Heron-Bench以解决日语视觉语言模型评估问题 multimodal
22 VIFNet: An End-to-end Visible-Infrared Fusion Network for Image Dehazing 提出VIFNet以解决图像去雾中的信息损失问题 multimodal ✅

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
23 Gaga: Group Any Gaussians via 3D-aware Memory Bank 提出Gaga框架以解决开放世界3D场景重建与分割问题 manipulation contrastive learning scene understanding
24 Uncovering the Metaverse within Everyday Environments: a Coarse-to-Fine Approach 提出基于视觉的Artcode标记方法以解决日常环境中的元宇宙链接问题 Apple Vision Pro

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

#题目一句话要点标签🔗⭐
25 AUG: A New Dataset and An Efficient Model for Aerial Image Urban Scene Graph Generation 提出AUG数据集与LPG模型以解决城市航拍图像场景图生成问题 spatial relationship

⬅️ 返回 cs.CV 首页 · 🏠 返回主页