cs.CV（2023-10-05）

📊 共 15 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

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

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
1	LumiNet: Perception-Driven Knowledge Distillation via Statistical Logit Calibration	提出LumiNet以解决logit蒸馏性能不足问题	distillation	✅
2	Can pre-trained models assist in dataset distillation?	利用预训练模型提升数据集蒸馏效果	distillation	✅
3	Expedited Training of Visual Conditioned Language Generation via Redundancy Reduction	提出EVLGen以加速视觉条件语言生成模型训练	representation learning large language model	✅
4	Ablation Study to Clarify the Mechanism of Object Segmentation in Multi-Object Representation Learning	通过消融研究揭示多目标表示学习中的物体分割机制	representation learning
5	RL-based Stateful Neural Adaptive Sampling and Denoising for Real-Time Path Tracing	提出基于RL的状态神经自适应采样与去噪以解决实时路径追踪问题	reinforcement learning spatiotemporal

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

#	题目	一句话要点	标签	🔗	⭐
6	Point-Based Radiance Fields for Controllable Human Motion Synthesis	提出基于点云的辐射场以实现可控的人体运动合成	neural radiance field motion synthesis human motion
7	Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation	提出Open-Fusion以解决实时开放词汇3D映射问题	scene reconstruction semantic map open-vocabulary	✅
8	BID-NeRF: RGB-D image pose estimation with inverted Neural Radiance Fields	提出BID-NeRF以解决RGB-D图像姿态估计问题	NeRF neural radiance field
9	FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators	提出FreeReg以解决图像与点云配准问题	monocular depth feature matching

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

#	题目	一句话要点	标签	🔗	⭐
10	Integrating Audio-Visual Features for Multimodal Deepfake Detection	提出音视频特征融合方法以解决深度伪造检测问题	multimodal
11	Investigating the Limitation of CLIP Models: The Worst-Performing Categories	提出类匹配边际以解决CLIP模型性能不足问题	large language model foundation model
12	Improved Baselines with Visual Instruction Tuning	通过视觉指令调优提升多模态模型基线性能	multimodal

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

#	题目	一句话要点	标签	🔗	⭐
13	Pose-Free Generalizable Rendering Transformer	提出Pose-Free框架以解决相机姿态依赖问题	feature matching	✅
14	Animatable Virtual Humans: Learning pose-dependent human representations in UV space for interactive performance synthesis	提出一种新型虚拟人表示以实现实时动画合成	SMPL

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
15	High-Degrees-of-Freedom Dynamic Neural Fields for Robot Self-Modeling and Motion Planning	提出动态神经场以解决机器人自我建模与运动规划问题	motion planning

⬅️ 返回 cs.CV 首页 · 🏠 返回主页