cs.CV（2023-11-15）

📊 共 13 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) (4 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗2) 支柱一：机器人控制 (Robot Control) (1) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱八：物理动画 (Physics-based Animation) (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 Spiking NeRF: Representing the Real-World Geometry by a Discontinuous Representation 提出Spiking NeRF以解决几何表示不连续性问题 NeRF ✅
2 Fast Certification of Vision-Language Models Using Incremental Randomized Smoothing 提出开放词汇认证方法以提升视觉语言模型的鲁棒性 open-vocabulary open vocabulary
3 RENI++ A Rotation-Equivariant, Scale-Invariant, Natural Illumination Prior 提出RENI++以解决逆向渲染中的自然光照先验问题 depth estimation ✅
4 DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model 提出DMV3D以解决多视角图像去噪问题 NeRF ✅

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

#题目一句话要点标签🔗⭐
5 Imagine the Unseen World: A Benchmark for Systematic Generalization in Visual World Models 提出系统视觉想象基准以解决机器学习中的系统组合性问题 world model world models
6 Toulouse Hyperspectral Data Set: a benchmark data set to assess semi-supervised spectral representation learning and pixel-wise classification techniques 发布图卢兹高光谱数据集以评估半监督光谱表示学习与像素级分类技术 representation learning masked autoencoder
7 Domain Aligned CLIP for Few-shot Classification 提出Domain Aligned CLIP以解决少样本分类问题 representation learning zero-shot transfer

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#题目一句话要点标签🔗⭐
8 Improving Zero-shot Visual Question Answering via Large Language Models with Reasoning Question Prompts 提出推理问题提示以改善零-shot视觉问答性能 large language model ✅
9 WildlifeDatasets: An open-source toolkit for animal re-identification 提出WildlifeDatasets工具包以解决动物重识别问题 foundation model ✅
10 One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Models 提出FedLMG以解决异构客户端的单次联邦学习问题 foundation model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
11 NormNet: Scale Normalization for 6D Pose Estimation in Stacked Scenarios 提出NormNet以解决堆叠场景中物体尺度变化问题 sim-to-real domain randomization 6D pose estimation

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
12 Cross-view and Cross-pose Completion for 3D Human Understanding 提出基于自监督学习的3D人类理解方法以解决数据不足问题 human mesh recovery human motion

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
13 Nothing Stands Still: A Spatiotemporal Benchmark on 3D Point Cloud Registration Under Large Geometric and Temporal Change 提出NSS基准以解决大规模时空变化下的3D点云配准问题 spatiotemporal

⬅️ 返回 cs.CV 首页 · 🏠 返回主页