cs.CV（2024-03-17）

📊 共 22 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (11 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (4 🔗1) 支柱五：交互与反应 (Interaction & Reaction) (2) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱六：视频提取与匹配 (Video Extraction) (2) 支柱七：动作重定向 (Motion Retargeting) (1 🔗1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (11 篇)

#题目一句话要点标签🔗⭐
1 Recent Advances in 3D Gaussian Splatting 提出3D高斯点云渲染以加速新视角合成 3D gaussian splatting 3DGS 3D reconstruction
2 3DGS-ReLoc: 3D Gaussian Splatting for Map Representation and Visual ReLocalization 提出3DGS-ReLoc以解决3D地图表示与视觉重定位问题 3D gaussian splatting 3DGS gaussian splatting
3 Compact 3D Gaussian Splatting For Dense Visual SLAM 提出紧凑型3D高斯点云以解决视觉SLAM中的冗余问题 visual SLAM 3D gaussian splatting gaussian splatting
4 Analytic-Splatting: Anti-Aliased 3D Gaussian Splatting via Analytic Integration 提出Analytic-Splatting以解决3D高斯点云渲染中的抗锯齿问题 3D gaussian splatting 3DGS gaussian splatting
5 Omni-Recon: Harnessing Image-based Rendering for General-Purpose Neural Radiance Fields 提出Omni-Recon以解决多任务3D重建问题 3D reconstruction NeRF neural radiance field
6 GeoGaussian: Geometry-aware Gaussian Splatting for Scene Rendering 提出GeoGaussian以解决场景渲染中的几何退化问题 gaussian splatting splatting
7 TAG: Guidance-free Open-Vocabulary Semantic Segmentation 提出TAG以解决无指导开放词汇语义分割问题 open-vocabulary open vocabulary ✅
8 Creating Seamless 3D Maps Using Radiance Fields 提出基于神经辐射场的3D地图重建方法以解决传统技术不足问题 gaussian splatting splatting NeRF
9 SpikeNeRF: Learning Neural Radiance Fields from Continuous Spike Stream 提出SpikeNeRF以解决真实场景中光照不理想的问题 NeRF neural radiance field ✅
10 Enhancing Bandwidth Efficiency for Video Motion Transfer Applications using Deep Learning Based Keypoint Prediction 提出深度学习关键点预测框架以提高视频运动传输的带宽效率 optical flow
11 Bilateral Propagation Network for Depth Completion 提出双边传播网络以解决深度补全问题 depth estimation

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

#题目一句话要点标签🔗⭐
12 CPA-Enhancer: Chain-of-Thought Prompted Adaptive Enhancer for Object Detection under Unknown Degradations 提出CPA-Enhancer以解决未知退化下的目标检测问题 chain-of-thought
13 Customizing Visual-Language Foundation Models for Multi-modal Anomaly Detection and Reasoning 提出多模态异常检测与推理的视觉语言基础模型 foundation model ✅
14 PhD: A ChatGPT-Prompted Visual hallucination Evaluation Dataset 提出ChatGPT辅助的视觉幻觉评估数据集以解决多模态大语言模型的幻觉问题 large language model multimodal
15 From Pixels to Predictions: Spectrogram and Vision Transformer for Better Time Series Forecasting 提出时频谱图与视觉变换器以改善时间序列预测 multimodal

🔬 支柱五：交互与反应 (Interaction & Reaction) (2 篇)

#题目一句话要点标签🔗⭐
16 THOR: Text to Human-Object Interaction Diffusion via Relation Intervention 提出THOR模型以解决动态人机交互生成问题 human-object interaction HOI human motion
17 FORCE: Physics-aware Human-object Interaction 提出FORCE模型以解决人机交互中的物理属性影响问题 human-object interaction human motion

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
18 BrightDreamer: Generic 3D Gaussian Generative Framework for Fast Text-to-3D Synthesis 提出BrightDreamer以解决文本到3D合成效率低下问题 dreamer distillation 3D gaussian splatting
19 Domain-Guided Masked Autoencoders for Unique Player Identification 提出领域引导的掩码自编码器以解决独特球员识别问题 masked autoencoder MAE

🔬 支柱六：视频提取与匹配 (Video Extraction) (2 篇)

#题目一句话要点标签🔗⭐
20 Diffusion Models are Efficient Data Generators for Human Mesh Recovery 提出HumanWild以解决3D人类姿态与形状估计问题 human mesh recovery SMPL SMPL-X
21 DynamicGlue: Epipolar and Time-Informed Data Association in Dynamic Environments using Graph Neural Networks 提出基于图神经网络的动态环境特征匹配方法以解决SLAM中的动态场景问题 feature matching

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

#题目一句话要点标签🔗⭐
22 Large Language Models Powered Context-aware Motion Prediction in Autonomous Driving 利用大语言模型提升自动驾驶中的运动预测精度 motion prediction large language model ✅

⬅️ 返回 cs.CV 首页 · 🏠 返回主页