cs.CV（2024-03-24）

📊 共 24 篇论文 | 🔗 10 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (10 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗3) 支柱九：具身大模型 (Embodied Foundation Models) (4 🔗2) 支柱一：机器人控制 (Robot Control) (3 🔗1) 支柱六：视频提取与匹配 (Video Extraction) (2 🔗1) 支柱四：生成式动作 (Generative Motion) (1 🔗1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (10 篇)

#题目一句话要点标签🔗⭐
1 Semantic Is Enough: Only Semantic Information For NeRF Reconstruction 提出仅基于语义信息的NeRF重建方法以提升3D场景理解 NeRF neural radiance field scene understanding
2 PKU-DyMVHumans: A Multi-View Video Benchmark for High-Fidelity Dynamic Human Modeling 提出PKU-DyMVHumans以解决动态人类建模问题 NeRF neural radiance field human motion
3 CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-aware 3D Gaussian Field 提出CG-SLAM以解决高效RGB-D SLAM中的不确定性问题 gaussian splatting splatting NeRF ✅
4 latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction 提出latentSplat以解决快速通用的3D重建问题 3D reconstruction splatting
5 Entity-NeRF: Detecting and Removing Moving Entities in Urban Scenes 提出Entity-NeRF以解决城市场景中动态物体去除问题 NeRF neural radiance field
6 Exploring Accurate 3D Phenotyping in Greenhouse through Neural Radiance Fields 提出基于神经辐射场的精准植物表型方法以解决温室环境下的表型挑战 NeRF neural radiance field
7 Self-Supervised Multi-Frame Neural Scene Flow 提出多帧点云场景流估计方法以提升自驾车的泛化能力 scene flow
8 Inverse Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fields 提出基于神经全光函数的逆向渲染方法以解决光滑物体重建问题 NeRF neural radiance field
9 AutoInst: Automatic Instance-Based Segmentation of LiDAR 3D Scans 提出AutoInst以解决LiDAR 3D扫描的实例分割问题 scene understanding ✅
10 Configurable Holography: Towards Display and Scene Adaptation 提出可配置全息技术以解决显示与场景适应性问题 depth estimation

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

#题目一句话要点标签🔗⭐
11 Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning 提出局部令牌遗忘以增强多模态对抗学习中的后门防御 contrastive learning multimodal
12 SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking 提出SDSTrack以解决多模态视觉目标跟踪中的模态差距问题 distillation multimodal ✅
13 Edit3K: Universal Representation Learning for Video Editing Components 提出Edit3K以解决视频编辑组件的表示学习问题 representation learning ✅
14 Exploring the Impact of Dataset Bias on Dataset Distillation 探讨数据集偏差对数据集蒸馏的影响 distillation ✅

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

#题目一句话要点标签🔗⭐
15 Towards Large-Scale Training of Pathology Foundation Models 提出可扩展的病理基础模型训练管道以提升医学图像分析 foundation model ✅
16 Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding 提出PU-VALOR以解决音视频事件时间理解问题 large language model multimodal
17 Object Detectors in the Open Environment: Challenges, Solutions, and Outlook 提出开放环境目标检测挑战框架以应对动态环境问题 foundation model ✅
18 Opportunities and challenges in the application of large artificial intelligence models in radiology 探讨大型人工智能模型在放射学中的应用机遇与挑战 multimodal

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
19 Low Rank Groupwise Deformations for Motion Tracking in Cardiac Cine MRI 提出低秩群体变形方法以解决心脏Cine MRI运动跟踪问题 motion tracking
20 Are NeRFs ready for autonomous driving? Towards closing the real-to-simulation gap 提出新方法以解决真实与模拟数据间的差距问题 real2sim NeRF neural radiance field
21 EVA: Zero-shot Accurate Attributes and Multi-Object Video Editing 提出EVA框架以解决视频编辑中的属性控制与布局保持问题 manipulation ✅

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

#题目一句话要点标签🔗⭐
22 EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World 提出EgoExoLearn数据集以解决异步视角下的程序性活动理解问题 egocentric multimodal ✅
23 Adversarially Masked Video Consistency for Unsupervised Domain Adaptation 提出基于对抗掩码视频一致性的方法以解决无监督领域适应问题 egocentric Ego4D

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
24 Gaze-guided Hand-Object Interaction Synthesis: Dataset and Method 提出注视引导的手物体交互合成方法以解决数据稀疏问题 motion generation HOI ✅

⬅️ 返回 cs.CV 首页 · 🏠 返回主页