cs.CV（2023-11-20）

📊 共 25 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) (7 🔗4) 支柱九：具身大模型 (Embodied Foundation Models) (6 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗1) 支柱六：视频提取与匹配 (Video Extraction) (2 🔗1) 支柱一：机器人控制 (Robot Control) (2) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (7 篇)

#题目一句话要点标签🔗⭐
1 GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting 提出GS-SLAM以解决实时SLAM系统中的效率与准确性平衡问题 visual SLAM 3D gaussian splatting gaussian splatting ✅
2 Toward Open Vocabulary Aerial Object Detection with CLIP-Activated Student-Teacher Learning 提出CastDet框架以解决开放词汇航空物体检测问题 open-vocabulary open vocabulary ✅
3 Entangled View-Epipolar Information Aggregation for Generalizable Neural Radiance Fields 提出EVE-NeRF以解决通用神经辐射场的视图聚合问题 NeRF neural radiance field ✅
4 A Multi-In-Single-Out Network for Video Frame Interpolation without Optical Flow 提出多输入单输出网络解决视频帧插值中的运动估计问题 optical flow
5 Mixing-Denoising Generalizable Occupancy Networks 提出仅基于MLP的占用网络以解决3D重建问题 3D reconstruction
6 PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction 提出PF-LRM以解决无姿态图像的3D重建问题 3D reconstruction ✅
7 ODDR: Outlier Detection & Dimension Reduction Based Defense Against Adversarial Patches 提出ODDR以应对基于补丁的对抗攻击问题 depth estimation

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

#题目一句话要点标签🔗⭐
8 LION : Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge 提出LION以解决多模态大语言模型视觉知识提取不足问题 large language model multimodal
9 DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding 提出DocPedia以解决高分辨率文档理解问题 large language model multimodal
10 VLM-Eval: A General Evaluation on Video Large Language Models 提出VLM-Eval以解决视频大语言模型评估不足问题 large language model
11 Multimodal deep learning for mapping forest dominant height by fusing GEDI with earth observation data 提出MARSNet以融合GEDI与遥感数据解决森林高度估计问题 multimodal
12 InfiMM-Eval: Complex Open-Ended Reasoning Evaluation For Multi-Modal Large Language Models 提出InfiMM-Eval以解决多模态大语言模型复杂推理评估问题 large language model ✅
13 LLMs as Visual Explainers: Advancing Image Classification with Evolving Visual Descriptions 提出基于进化优化的LLMs与VLMs结合框架以提升图像分类准确性 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
14 GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understanding 提出GP-NeRF以解决上下文感知3D场景理解问题 distillation NeRF scene understanding
15 Applications of Large Scale Foundation Models for Autonomous Driving 结合基础模型与大语言模型以重塑自动驾驶系统 world model world models large language model
16 BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning 提出BadCLIP以解决多模态对比学习中的后门攻击问题 contrastive learning multimodal
17 Few-shot Multispectral Segmentation with Representations Generated by Reinforcement Learning 提出基于强化学习的少样本多光谱图像分割方法 reinforcement learning ✅
18 OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning 提出OmniSeg3D以解决多样化3D场景分割问题 contrastive learning
19 FreeKD: Knowledge Distillation via Semantic Frequency Prompt 提出FreeKD以解决知识蒸馏中的特征图失真问题 distillation

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

#题目一句话要点标签🔗⭐
20 LiDAR-HMR: 3D Human Mesh Recovery from LiDAR 提出稀疏到密集重建方案以解决LiDAR点云下的人体网格恢复问题 human mesh recovery HMR ✅
21 Semantic-Preserved Point-based Human Avatar 提出点基人类头像模型以提升AR/VR体验 SMPL SMPL-X

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
22 SeaDSC: A video-based unsupervised method for dynamic scene change detection in unmanned surface vehicles 提出SeaDSC以解决无人水面车辆动态场景变化检测问题 motion planning scene understanding VQ-VAE
23 Video Face Re-Aging: Toward Temporally Consistent Face Re-Aging 提出视频人脸再衰老方法以解决时间一致性问题 manipulation

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

#题目一句话要点标签🔗⭐
24 Enhanced Spatio-Temporal Context for Temporally Consistent Robust 3D Human Motion Recovery from Monocular Videos 提出一种新方法以解决单目视频中3D人类运动恢复问题 human motion human motion recovery motion recovery

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
25 DiffAvatar: Simulation-Ready Garment Optimization with Differentiable Simulation 提出DiffAvatar以解决数字化服装资产生成问题 physically plausible differentiable simulation

⬅️ 返回 cs.CV 首页 · 🏠 返回主页