cs.CV（2024-02-09）

📊 共 17 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (8 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (6 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗2) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (8 篇)

#题目一句话要点标签🔗⭐
1 GS-CLIP: Gaussian Splatting for Contrastive Language-Image-3D Pretraining from Real-World Data 提出GS-CLIP以解决3D点云表示与2D对应关系的差距问题 3D gaussian splatting 3DGS gaussian splatting
2 Neural Rendering based Urban Scene Reconstruction for Autonomous Driving 提出多模态3D场景重建方法以解决自动驾驶中的深度估计问题 3D reconstruction scene reconstruction multimodal
3 Deepfake for the Good: Generating Avatars through Face-Swapping with Implicit Deepfake Generation 提出隐式深伪技术以生成更真实的3D头像 gaussian splatting splatting NeRF
4 Oriented-grid Encoder for 3D Implicit Representations 提出面向网格编码器以改进3D隐式表示 implicit representation
5 Hybridnet for depth estimation and semantic segmentation 提出HybridNet以解决深度估计与语义分割的联合问题 depth estimation
6 A Network for structural dense displacement based on 3D deformable mesh model and optical flow 提出基于3D可变形网格模型和光流的网络以识别结构位移 optical flow
7 Image-based Deep Learning for the time-dependent prediction of fresh concrete properties 提出基于图像的深度学习方法以预测新鲜混凝土特性 optical flow
8 SIR: Multi-view Inverse Rendering with Decomposable Shadow Under Indoor Intense Lighting 提出SIR以解决室内强光环境下阴影分解问题 neural radiance field ✅

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

#题目一句话要点标签🔗⭐
9 On the Out-Of-Distribution Generalization of Multimodal Large Language Models 提出在上下文学习中增强多模态大语言模型的泛化能力 large language model multimodal
10 ViGoR: Improving Visual Grounding of Large Vision Language Models with Fine-Grained Reward Modeling 提出ViGoR以解决大型视觉语言模型的视觉定位问题 large language model visual grounding ✅
11 Iris-SAM: Iris Segmentation Using a Foundation Model 提出Iris-SAM以解决虹膜分割问题 foundation model
12 Large Language Models for Captioning and Retrieving Remote Sensing Images 提出RS-CapRet以解决遥感图像的描述与检索问题 large language model
13 Video Annotator: A framework for efficiently building video classifiers using vision-language models and active learning 提出视频注释框架以解决视频分类标注效率低下问题 foundation model ✅
14 ContPhy: Continuum Physical Concept Learning and Reasoning from Videos 提出ContPhy数据集以解决机器物理常识推理问题 large language model

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

#题目一句话要点标签🔗⭐
15 HeadStudio: Text to Animatable Head Avatars with 3D Gaussian Splatting 提出HeadStudio以解决高质量动画头像生成问题 distillation 3D gaussian splatting gaussian splatting ✅
16 FD-Vision Mamba for Endoscopic Exposure Correction 提出FD-Vision Mamba以解决内窥镜图像曝光异常问题 Mamba SSM ✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
17 Is it safe to cross? Interpretable Risk Assessment with GPT-4V for Safety-Aware Street Crossing 提出基于GPT-4V的可解释风险评估方法以解决盲人安全过马路问题 quadruped egocentric multimodal

⬅️ 返回 cs.CV 首页 · 🏠 返回主页