cs.CV（2023-11-16）

📊 共 12 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (5) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱九：具身大模型 (Embodied Foundation Models) (2 🔗2) 支柱六：视频提取与匹配 (Video Extraction) (2)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Neural-Logic Human-Object Interaction Detection	提出L OGIC HOI以解决传统HOI检测方法的局限性	affordance human-object interaction HOI
2	Depth Insight -- Contribution of Different Features to Indoor Single-image Depth Estimation	量化室内单幅图像深度估计中不同特征的贡献	depth estimation monocular depth
3	Adaptive Shells for Efficient Neural Radiance Field Rendering	提出自适应外壳以提高神经辐射场渲染效率	neural radiance field
4	EvaSurf: Efficient View-Aware Implicit Textured Surface Reconstruction	提出EvaSurf以解决高效的视角感知隐式纹理表面重建问题	3D reconstruction NeRF neural radiance field
5	Reconstructing Continuous Light Field From Single Coded Image	提出从单幅编码图像重建连续光场的方法	NeRF neural radiance field

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

#	题目	一句话要点	标签	🔗	⭐
6	Efficient End-to-End Visual Document Understanding with Rationale Distillation	提出Rationale Distillation以解决视觉文档理解问题	distillation large language model multimodal
7	DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback	提出DRESS以解决现有视觉语言模型交互不足问题	reinforcement learning large language model
8	MetaDreamer: Efficient Text-to-3D Creation With Disentangling Geometry and Texture	提出MetaDreamer以解决3D生成中的几何与纹理纠缠问题	dreamer

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

#	题目	一句话要点	标签	🔗	⭐
9	UnifiedVisionGPT: Streamlining Vision-Oriented AI through Generalized Multimodal Framework	提出UnifiedVisionGPT以整合视觉模型，推动视觉AI发展	large language model foundation model multimodal	✅
10	RED-DOT: Multimodal Fact-checking via Relevant Evidence Detection	提出RED-DOT以解决多模态事实核查中的相关证据检测问题	multimodal	✅

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

#	题目	一句话要点	标签	🔗	⭐
11	Temporal-Aware Refinement for Video-based Human Pose and Shape Recovery	提出时间感知精炼网络以解决视频中人体姿态与形状恢复问题	SMPL human motion
12	Match and Locate: low-frequency monocular odometry based on deep feature matching	提出基于深度特征匹配的低频单目里程计以解决姿态估计问题	feature matching

⬅️ 返回 cs.CV 首页 · 🏠 返回主页