cs.CV(2024-03-23)

📊 共 13 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) (4 🔗2) 支柱二:RL算法与架构 (RL & Architecture) (3 🔗1) 支柱一:机器人控制 (Robot Control) (2) 支柱九:具身大模型 (Embodied Foundation Models) (2) 支柱四:生成式动作 (Generative Motion) (1 🔗1) 支柱五:交互与反应 (Interaction & Reaction) (1)

🔬 支柱三:空间感知与语义 (Perception & Semantics) (4 篇)

#题目一句话要点标签🔗
1 Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collections 提出GS-W以解决无约束图像集合的3D重建问题 3D gaussian splatting gaussian splatting splatting
2 SUP-NeRF: A Streamlined Unification of Pose Estimation and NeRF for Monocular 3D Object Reconstruction 提出SUP-NeRF以解决单目3D重建中的姿态估计问题 3D reconstruction NeRF
3 Depth Estimation fusing Image and Radar Measurements with Uncertain Directions 提出融合图像与雷达测量的深度估计方法以解决不确定方向问题 depth estimation
4 DS-NeRV: Implicit Neural Video Representation with Decomposed Static and Dynamic Codes 提出DS-NeRV以解决视频静态与动态信息混淆问题 optical flow

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

#题目一句话要点标签🔗
5 iDAT: inverse Distillation Adapter-Tuning 提出逆蒸馏适配器调优方法以提升微调性能 distillation
6 SceneX: Procedural Controllable Large-scale Scene Generation 提出SceneX以解决大规模场景生成中的控制性不足问题 world model world models
7 Technical Report: Masked Skeleton Sequence Modeling for Learning Larval Zebrafish Behavior Latent Embeddings 提出Masked Skeleton Sequence建模方法以学习幼鱼行为潜在嵌入 masked autoencoder MAE

🔬 支柱一:机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗
8 Advanced Feature Manipulation for Enhanced Change Detection Leveraging Natural Language Models 提出基于自然语言模型的特征处理方法以增强变化检测 manipulation large language model
9 Deep Domain Adaptation: A Sim2Real Neural Approach for Improving Eye-Tracking Systems 提出一种Sim2Real神经网络方法以改善眼动追踪系统 sim2real

🔬 支柱九:具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗
10 IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models 提出IllusionVQA数据集以评估视觉语言模型在光学错觉中的表现 chain-of-thought
11 Temporal-Spatial Object Relations Modeling for Vision-and-Language Navigation 提出时空对象关系建模以解决视觉与语言导航问题 VLN

🔬 支柱四:生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗
12 Contact-aware Human Motion Generation from Textual Descriptions 提出CATMO以解决文本驱动的人体运动生成问题 text-to-motion motion synthesis motion generation

🔬 支柱五:交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗
13 Human Motion Prediction under Unexpected Perturbation 提出LDP模型以解决人类运动在意外扰动下的预测问题 reactive motion human motion human motion prediction

⬅️ 返回 cs.CV 首页 · 🏠 返回主页