cs.CV（2024-03-31）

📊 共 16 篇论文 | 🔗 9 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) (4 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗4) 支柱六：视频提取与匹配 (Video Extraction) (2 🔗2) 支柱四：生成式动作 (Generative Motion) (1 🔗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 Neural Radiance Field-based Visual Rendering: A Comprehensive Review 综述神经辐射场技术以推动3D场景理解与重建 NeRF neural radiance field scene understanding
2 Training-Free Semantic Segmentation via LLM-Supervision 提出无训练语义分割方法以提升分类精度 open-vocabulary open vocabulary large language model
3 OmniSDF: Scene Reconstruction using Omnidirectional Signed Distance Functions and Adaptive Binoctrees 提出OmniSDF以解决小基线场景重建问题 scene reconstruction
4 Knowledge NeRF: Few-shot Novel View Synthesis for Dynamic Articulated Objects 提出Knowledge NeRF以解决动态关节物体的少量视图合成问题 NeRF ✅
5 Towards Realistic Scene Generation with LiDAR Diffusion Models 提出LiDAR扩散模型以解决LiDAR场景生成的挑战 semantic map

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
6 M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models 提出M3D以推进3D医学图像分析 large language model ✅
7 Rethinking Interactive Image Segmentation with Low Latency, High Quality, and Diverse Prompts 提出SegNext以解决低延迟、高质量的交互式图像分割问题 foundation model
8 LLM meets Vision-Language Models for Zero-Shot One-Class Classification 提出一种新方法解决零样本单类视觉分类问题 large language model
9 LLMs are Good Action Recognizers 提出LLM-AR框架以提升骨架动作识别精度 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
10 Weak-to-Strong 3D Object Detection with X-Ray Distillation 提出X-Ray蒸馏方法以解决LiDAR三维物体检测中的稀疏与遮挡问题 teacher-student distillation ✅
11 Disentangling Hippocampal Shape Variations: A Study of Neurological Disorders Using Mesh Variational Autoencoder with Contrastive Learning 提出基于网格变分自编码器的对比学习以解析海马形状变化 contrastive learning ✅
12 Exploiting Inter-sample and Inter-feature Relations in Dataset Distillation 提出类中心化约束与协方差匹配约束以解决数据集蒸馏问题 distillation ✅
13 Modeling State Shifting via Local-Global Distillation for Event-Frame Gaze Tracking 提出基于局部-全局蒸馏的状态转移建模方法以解决被动注视估计问题 distillation ✅

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

#题目一句话要点标签🔗⭐
14 $R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding 提出$R^2$-Tuning以解决视频时序定位问题 Ego4D ✅
15 TexVocab: Texture Vocabulary-conditioned Human Avatars 提出TexVocab以解决多视角视频建模中的纹理表示问题 SMPL ✅

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
16 Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interaction 提出Text2HOI以解决3D手物交互生成问题 motion generation physically plausible penetration ✅

⬅️ 返回 cs.CV 首页 · 🏠 返回主页