cs.CV（2023-11-05）

📊 共 11 篇论文 | 🔗 3 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) (3 🔗2) 支柱一：机器人控制 (Robot Control) (3)

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

#	题目	一句话要点	标签	🔗	⭐
1	VR-NeRF: High-Fidelity Virtualized Walkable Spaces	提出VR-NeRF以实现高保真虚拟步行空间的实时渲染	NeRF neural radiance field
2	MuSHRoom: Multi-Sensor Hybrid Room Dataset for Joint 3D Reconstruction and Novel View Synthesis	提出MuSHRoom数据集以解决3D重建与新视角合成的统一建模问题	3D reconstruction	✅
3	CCMR: High Resolution Optical Flow Estimation via Coarse-to-Fine Context-Guided Motion Reasoning	提出CCMR以解决高分辨率光流估计问题	optical flow
4	IPVNet: Learning Implicit Point-Voxel Features for Open-Surface 3D Reconstruction	提出IPVNet以解决开放表面3D重建问题	3D reconstruction
5	The Background Also Matters: Background-Aware Motion-Guided Objects Discovery	提出背景感知运动引导的物体发现方法以解决背景处理不足问题	optical flow

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
6	ChEF: A Comprehensive Evaluation Framework for Standardized Assessment of Multimodal Large Language Models	提出ChEF框架以标准化评估多模态大语言模型	large language model multimodal instruction following
7	Octavius: Mitigating Task Interference in MLLMs via LoRA-MoE	提出Octavius以解决多模态学习中的任务干扰问题	large language model multimodal	✅
8	GPT-4V-AD: Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly Detection	提出GPT-4V-AD以解决零-shot异常检测问题	multimodal visual grounding	✅

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
9	AV-Lip-Sync+: Leveraging AV-HuBERT to Exploit Multimodal Inconsistency for Deepfake Detection of Frontal Face Videos	提出AV-Lip-Sync+以解决多模态深fake检测问题	manipulation multimodal
10	Synthetic Tumor Manipulation: With Radiomics Features	提出RadiomicsFill以生成合成肿瘤并控制特征	manipulation
11	Fast Point Cloud to Mesh Reconstruction for Deformable Object Tracking	提出快速点云到网格重建方法以解决可变形物体跟踪问题	dexterous hand 3D reconstruction

⬅️ 返回 cs.CV 首页 · 🏠 返回主页