cs.CV（2024-04-22）

📊 共 27 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) (9) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (7 🔗3) 支柱八：物理动画 (Physics-based Animation) (1) 支柱七：动作重定向 (Motion Retargeting) (1 🔗1) 支柱六：视频提取与匹配 (Video Extraction) (1 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (9 篇)

#题目一句话要点标签🔗⭐
1 GaussianTalker: Speaker-specific Talking Head Synthesis via 3D Gaussian Splatting 提出GaussianTalker以解决音频驱动的说话人特定合成问题 3D gaussian splatting gaussian splatting splatting
2 CT-NeRF: Incremental Optimizing Neural Radiance Field and Poses with Complex Trajectory 提出CT-NeRF以解决复杂轨迹下相机姿态优化问题 NeRF neural radiance field scene reconstruction
3 Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpses 提出动态3D场景重建方法以解决稀疏观察问题 3D gaussian splatting gaussian splatting splatting
4 Self-Supervised Monocular Depth Estimation in the Dark: Towards Data Distribution Compensation 提出一种无夜间图像的自监督单目深度估计方法以解决夜间图像监督不足问题 depth estimation monocular depth
5 Neural Radiance Field in Autonomous Driving: A Survey 综述NeRF在自动驾驶中的应用以填补文献空白 3D reconstruction NeRF neural radiance field
6 NeRF-DetS: Enhanced Adaptive Spatial-wise Sampling and View-wise Fusion Strategies for NeRF-based Indoor Multi-view 3D Object Detection 提出NeRF-DetS以解决室内多视角3D物体检测中的采样与融合问题 NeRF implicit representation
7 CloudFort: Enhancing Robustness of 3D Point Cloud Classification Against Backdoor Attacks via Spatial Partitioning and Ensemble Prediction 提出CloudFort以增强3D点云分类对后门攻击的鲁棒性 scene understanding
8 Structure-Aware Human Body Reshaping with Adaptive Affinity-Graph Network 提出自适应亲和图网络以解决人体重塑中的一致性问题 optical flow
9 On Support Relations Inference and Scene Hierarchy Graph Construction from Point Cloud in Clustered Environments 提出基于点云的支持关系推断与场景层次图构建方法 scene understanding

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
10 CLIP-GS: CLIP-Informed Gaussian Splatting for View-Consistent 3D Indoor Semantic Understanding 提出CLIP-GS以解决3D室内语义理解中的一致性问题 SAC 3D gaussian splatting 3DGS
11 A Multimodal Feature Distillation with Mamba-Transformer Network for Brain Tumor Segmentation with Incomplete Modalities 提出多模态特征蒸馏方法解决脑肿瘤分割中的模态缺失问题 Mamba distillation multimodal
12 CKD: Contrastive Knowledge Distillation from A Sample-wise Perspective 提出对比知识蒸馏框架以解决样本间语义一致性问题 teacher-student distillation
13 MambaUIE&SR: Unraveling the Ocean's Secrets with Only 2.8 GFLOPs 提出MambaUIE以高效解决水下图像增强问题 Mamba SSM ✅
14 Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback 提出细粒度AI反馈以解决大规模视觉语言模型中的幻觉问题 preference learning DPO direct preference optimization
15 OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks 提出OccFeat以解决BEV语义分割网络的预训练问题 distillation foundation model ✅
16 PGAHum: Prior-Guided Geometry and Appearance Learning for High-Fidelity Animatable Human Reconstruction 提出PGAHum以解决高保真可动画人类重建问题 representation learning SMPL

🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)

#题目一句话要点标签🔗⭐
17 SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation 提出SEED-X以解决多模态模型在现实应用中的不足 foundation model multimodal ✅
18 Zero-Shot Character Identification and Speaker Prediction in Comics via Iterative Multimodal Fusion 提出零-shot方法解决漫画角色识别与说话者预测问题 large language model multimodal
19 Narrative Action Evaluation with Prompt-Guided Multimodal Interaction 提出基于提示引导的多模态交互框架以解决叙事动作评估问题 multimodal ✅
20 Graphic Design with Large Multimodal Model 提出层次化布局生成方法以解决图形设计中的元素整合问题 multimodal ✅
21 EventLens: Leveraging Event-Aware Pretraining and Cross-modal Linking Enhances Visual Commonsense Reasoning 提出EventLens以解决视觉常识推理中的知识激活问题 large language model multimodal
22 "Where am I?" Scene Retrieval with Language 提出Text2SceneGraphMatcher以解决语言场景检索问题 embodied AI
23 AutoAD III: The Prequel -- Back to the Pixels 提出新方法生成电影音频描述以解决数据不足问题 large language model

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

#题目一句话要点标签🔗⭐
24 A Stochastic Geo-spatiotemporal Bipartite Network to Optimize GCOOS Sensor Placement Strategies 提出随机地理时空双边网络优化GCOOS传感器布局策略 spatiotemporal

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

#题目一句话要点标签🔗⭐
25 PeLiCal: Targetless Extrinsic Calibration via Penetrating Lines for RGB-D Cameras with Limited Co-visibility 提出PeLiCal以解决RGB-D相机外部标定问题 motion estimation ✅

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

#题目一句话要点标签🔗⭐
26 Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizer 提出基于场景坐标重建的图像集合定位方法 feature matching ✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
27 Swap It Like Its Hot: Segmentation-based spoof attacks on eye-tracking images 提出IrisSwap以解决眼动追踪图像的伪造攻击问题 manipulation

⬅️ 返回 cs.CV 首页 · 🏠 返回主页