cs.CV（2023-10-20）

📊 共 13 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (4 🔗3) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (4 篇)

#	题目	一句话要点	标签	🔗	⭐
1	OpenAnnotate3D: Open-Vocabulary Auto-Labeling System for Multi-modal 3D Data	提出OpenAnnotate3D以解决多模态3D数据的自动标注问题	open-vocabulary open vocabulary embodied AI
2	UE4-NeRF:Neural Radiance Field for Real-Time Rendering of Large-Scale Scene	提出UE4-NeRF以解决大规模场景实时渲染问题	3D reconstruction NeRF neural radiance field	✅
3	Sync-NeRF: Generalizing Dynamic NeRFs to Unsynchronized Videos	提出Sync-NeRF以解决动态NeRF在非同步视频中的重建问题	NeRF neural radiance field scene reconstruction	✅
4	ManifoldNeRF: View-dependent Image Feature Supervision for Few-shot Neural Radiance Fields	提出ManifoldNeRF以解决少量图像下的视角依赖特征监督问题	NeRF neural radiance field	✅

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

#	题目	一句话要点	标签	🔗	⭐
5	Benchmarking Sequential Visual Input Reasoning and Prediction in Multimodal Large Language Models	提出多模态大语言模型预测推理基准以解决能力不足问题	large language model multimodal
6	Bridging the Gap between Synthetic and Authentic Images for Multimodal Machine Translation	提出一种方法以解决合成图像与真实图像之间的差距问题	multimodal
7	Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worlds	提出Steve-Eye以解决LLM代理视觉感知不足问题	large language model multimodal

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
8	SILC: Improving Vision Language Pretraining with Self-Distillation	提出SILC框架以提升视觉语言预训练效果	contrastive learning distillation open-vocabulary
9	Data-Free Knowledge Distillation Using Adversarially Perturbed OpenGL Shader Images	提出一种新方法以解决无数据知识蒸馏问题	distillation
10	Learning with Unmasked Tokens Drives Stronger Vision Learners	通过引入未掩码标记提升视觉学习者的表现	masked autoencoder MAE	✅

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

#	题目	一句话要点	标签	🔗	⭐
11	PACE: Human and Camera Motion Estimation from in-the-wild Videos	提出一种新方法以解决动态视频中的人类与相机运动估计问题	human motion motion estimation

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
12	FMRT: Learning Accurate Feature Matching with Reconciliatory Transformer	提出FMRT以解决特征匹配精度不足问题	feature matching

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
13	Dance Your Latents: Consistent Dance Generation through Spatial-temporal Subspace Attention Guided by Motion Flow	提出Dance-Your-Latents以解决舞蹈生成中的时空一致性问题	spatiotemporal

⬅️ 返回 cs.CV 首页 · 🏠 返回主页