cs.CV(2023-12-04)

📊 共 9 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 🔗1) 支柱九:具身大模型 (Embodied Foundation Models) (2 🔗1) 支柱四:生成式动作 (Generative Motion) (1) 支柱七:动作重定向 (Motion Retargeting) (1)

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

#题目一句话要点标签🔗
1 SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes 提出SC-GS,通过稀疏控制高斯溅射实现动态场景的可编辑新视角合成。 gaussian splatting splatting
2 PointNeRF++: A multi-scale, point-based Neural Radiance Field PointNeRF++:提出一种多尺度、基于点的神经辐射场,提升稀疏点云场景渲染质量。 NeRF neural radiance field
3 SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM SplaTAM:利用3D高斯模型进行密集RGB-D SLAM,实现高保真重建 SplaTAM
4 Re-Nerfing: Improving Novel View Synthesis through Novel View Synthesis Re-Nerfing:通过新视角合成改进新视角合成,提升稀疏视角下的NeRF性能 gaussian splatting splatting NeRF
5 Mathematical Supplement for the $\texttt{gsplat}$ Library 为高效可微高斯溅射库gsplat提供数学细节补充 gaussian splatting splatting NeRF

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

#题目一句话要点标签🔗
6 TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding 提出TimeChat,一种时间敏感的多模态大语言模型,用于长视频理解。 large language model multimodal instruction following
7 Mitigating Fine-Grained Hallucination by Fine-Tuning Large Vision-Language Models with Caption Rewrites 提出ReCaption框架,通过重写Caption微调LVLM,缓解细粒度幻觉问题 large language model

🔬 支柱四:生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗
8 EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation 提出EMDM高效运动扩散模型,实现快速高质量的人体运动生成 motion diffusion model motion diffusion motion generation

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

#题目一句话要点标签🔗
9 Semantics-aware Motion Retargeting with Vision-Language Models 提出一种语义感知的运动重定向方法,利用视觉-语言模型提取和保持运动语义。 motion retargeting

⬅️ 返回 cs.CV 首页 · 🏠 返回主页