cs.CV（2023-11-06）

📊 共 21 篇论文 | 🔗 7 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (6 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (5 🔗2) 支柱一：机器人控制 (Robot Control) (4 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗2) 支柱八：物理动画 (Physics-based Animation) (2) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (6 篇)

#题目一句话要点标签🔗⭐
1 Rethinking Evaluation Metrics of Open-Vocabulary Segmentaion 提出开放词汇分割的新评估指标以解决现有方法的不足 open-vocabulary open vocabulary
2 Animating NeRFs from Texture Space: A Framework for Pose-Dependent Rendering of Human Performances 提出基于NeRF的框架以解决动态人类表演渲染问题 NeRF neural radiance field SMPL
3 InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image 提出InstructPix2NeRF以解决开放世界肖像的3D编辑问题 NeRF neural radiance field ✅
4 Toward Planet-Wide Traffic Camera Calibration 提出一种可扩展框架以解决交通摄像头校准问题 scene reconstruction
5 Long-Term Invariant Local Features via Implicit Cross-Domain Correspondences 提出隐式跨域对应方法以解决长期视觉定位问题 neural radiance field
6 Consistent4D: Consistent 360° Dynamic Object Generation from Monocular Video 提出Consistent4D以解决单目视频动态物体生成问题 neural radiance field ✅

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
7 GLaMM: Pixel Grounding Large Multimodal Model 提出GLaMM以解决多模态模型的对象分割与生成问题 large language model multimodal
8 CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding 提出CoVLM以解决视觉语言模型的组合推理问题 large language model foundation model
9 Multimodal Stress Detection Using Facial Landmarks and Biometric Signals 提出多模态学习方法以提高压力检测准确性 multimodal
10 LCPR: A Multi-Scale Attention-Based LiDAR-Camera Fusion Network for Place Recognition 提出LCPR以解决多模态场景识别中的传感器融合问题 multimodal ✅
11 CogVLM: Visual Expert for Pretrained Language Models 提出CogVLM以解决视觉与语言模型融合问题 foundation model ✅

🔬 支柱一：机器人控制 (Robot Control) (4 篇)

#题目一句话要点标签🔗⭐
12 OVIR-3D: Open-Vocabulary 3D Instance Retrieval Without Training on 3D Data 提出OVIR-3D以解决无3D数据训练的开放词汇3D实例检索问题 manipulation open-vocabulary open vocabulary
13 Exploitation-Guided Exploration for Semantic Embodied Navigation 提出基于利用引导的探索方法以提升语义体导航性能 sim-to-real
14 LDM3D-VR: Latent Diffusion Model for 3D VR 提出LDM3D-VR以解决3D虚拟现实中的深度图生成问题 manipulation
15 Human as Points: Explicit Point-based 3D Human Reconstruction from Single-view RGB Images 提出HaP框架以解决单视角人类重建的灵活性和鲁棒性问题 manipulation ✅

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

#题目一句话要点标签🔗⭐
16 Asymmetric Masked Distillation for Pre-Training Small Foundation Models 提出不对称掩码蒸馏以高效预训练小型基础模型 MAE distillation foundation model ✅
17 TSP-Transformer: Task-Specific Prompts Boosted Transformer for Holistic Scene Understanding 提出TSP-Transformer以提升整体场景理解能力 representation learning depth estimation scene understanding ✅
18 Unified Multi-modal Unsupervised Representation Learning for Skeleton-based Action Understanding 提出UmURL框架以解决骨骼动作理解中的多模态冗余问题 representation learning multimodal

🔬 支柱八：物理动画 (Physics-based Animation) (2 篇)

#题目一句话要点标签🔗⭐
19 Flexible Multi-Generator Model with Fused Spatiotemporal Graph for Trajectory Prediction 提出融合时空图的多生成器模型以解决轨迹预测问题 spatiotemporal
20 SoundCam: A Dataset for Finding Humans Using Room Acoustics 提出SoundCam数据集以解决人类检测与定位问题 PULSE

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

#题目一句话要点标签🔗⭐
21 Unsupervised Region-Growing Network for Object Segmentation in Atmospheric Turbulence 提出无监督区域生长网络以解决大气湍流下的物体分割问题 geometric consistency

⬅️ 返回 cs.CV 首页 · 🏠 返回主页