cs.CV（2023-11-21）

📊 共 22 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (6 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (5 🔗1) 支柱一：机器人控制 (Robot Control) (4 🔗1) 支柱七：动作重定向 (Motion Retargeting) (3) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1) 支柱六：视频提取与匹配 (Video Extraction) (2 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#题目一句话要点标签🔗⭐
1 Enhancing Visual Grounding and Generalization: A Multi-Task Cycle Training Approach for Vision-Language Models 提出ViLaM以解决多任务视觉定位问题 large language model visual grounding ✅
2 Boosting Audio-visual Zero-shot Learning with Large Language Models 提出KDA框架以提升音视频零-shot学习能力 large language model ✅
3 SPOT! Revisiting Video-Language Models for Event Understanding 提出SPOT Prober以解决视频语言模型事件理解能力不足的问题 multimodal TAMP
4 Descriptor and Word Soups: Overcoming the Parameter Efficiency Accuracy Tradeoff for Out-of-Distribution Few-shot Learning 提出描述符与词汇汤以解决少样本OOD学习中的参数效率问题 multimodal
5 KNVQA: A Benchmark for evaluation knowledge-based VQA 提出KNVQA以解决知识基础VQA评估问题 multimodal
6 TouchSDF: A DeepSDF Approach for 3D Shape Reconstruction using Vision-Based Tactile Sensing 提出TouchSDF以解决基于触觉传感的3D形状重建问题 multimodal

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

#题目一句话要点标签🔗⭐
7 Hyb-NeRF: A Multiresolution Hybrid Encoding for Neural Radiance Fields 提出Hyb-NeRF以解决NeRF渲染速度慢和内存占用高的问题 NeRF neural radiance field scene reconstruction
8 Camera-Independent Single Image Depth Estimation from Defocus Blur 提出无关相机的单幅图像模糊深度估计方法以解决现有技术的局限性 depth estimation monocular depth ✅
9 IMJENSE: Scan-specific Implicit Representation for Joint Coil Sensitivity and Image Estimation in Parallel MRI 提出IMJENSE以解决并行MRI重建中的图像质量问题 implicit representation
10 Physics-guided Shape-from-Template: Monocular Video Perception through Neural Surrogate Models 提出基于物理引导的模板形状重建以解决动态场景重建问题 3D reconstruction
11 Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation 提出深度感知框架以解决场景适应问题 depth estimation

🔬 支柱一：机器人控制 (Robot Control) (4 篇)

#题目一句话要点标签🔗⭐
12 RFTrans: Leveraging Refractive Flow of Transparent Objects for Surface Normal Estimation and Manipulation 提出RFTrans以解决透明物体表面法线估计与操控问题 manipulation sim-to-real physically plausible
13 Learning Part Motion of Articulated Objects Using Spatially Continuous Neural Implicit Representations 提出空间连续神经隐式表示以解决关节物体运动建模问题 manipulation implicit representation
14 Mobile-Seed: Joint Semantic Segmentation and Boundary Detection for Mobile Robots 提出Mobile-Seed以解决移动机器人语义分割与边界检测问题 manipulation semantic mapping semantic map ✅
15 Multi-Resolution Planar Region Extraction for Uneven Terrains 提出多分辨率平面区域提取方法以解决不平坦地形问题 locomotion

🔬 支柱七：动作重定向 (Motion Retargeting) (3 篇)

#题目一句话要点标签🔗⭐
16 MaskFlow: Object-Aware Motion Estimation 提出MaskFlow以解决复杂场景下的运动估计问题 motion estimation
17 HiFi-Syn: Hierarchical Granularity Discrimination for High-Fidelity Synthesis of MR Images with Structure Preservation 提出层次粒度判别以解决医学图像合成中的结构保留问题 structure preservation
18 ShareGPT4V: Improving Large Multi-Modal Models with Better Captions 提出ShareGPT4V以解决多模态模型数据稀缺问题 spatial relationship

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
19 Diffusion Model Alignment Using Direct Preference Optimization 提出Diffusion-DPO以优化扩散模型对人类偏好的对齐 reinforcement learning preference learning RLHF
20 Point, Segment and Count: A Generalized Framework for Object Counting 提出PseCo框架以解决少样本与零样本目标计数问题 distillation foundation model ✅

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

#题目一句话要点标签🔗⭐
21 Novel OCT mosaicking pipeline with Feature- and Pixel-based registration 提出一种新型OCT图像拼接管道以解决视场限制问题 feature matching ✅
22 Polyhedral Object Recognition by Indexing 提出基于图索引的三维多面体物体识别方法 feature matching

⬅️ 返回 cs.CV 首页 · 🏠 返回主页