cs.CV（2023-10-09）

📊 共 12 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

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

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

#题目一句话要点标签🔗⭐
1 WeatherDepth: Curriculum Contrastive Learning for Self-Supervised Depth Estimation under Adverse Weather Conditions 提出WeatherDepth以解决恶劣天气下深度估计问题 contrastive learning curriculum learning depth estimation ✅
2 Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching 提出基于难度对齐轨迹匹配的无损数据集蒸馏方法 distillation ✅
3 Adaptive Multi-head Contrastive Learning 提出自适应多头对比学习以解决对比学习中的相似性评估问题 contrastive learning
4 Semantic-aware Temporal Channel-wise Attention for Cardiac Function Assessment 提出语义感知时序通道注意力以改善心脏功能评估 representation learning MAE

🔬 支柱三：空间感知与语义 (Perception & Semantics) (3 篇)

#题目一句话要点标签🔗⭐
5 HarmonicNeRF: Geometry-Informed Synthetic View Augmentation for 3D Scene Reconstruction in Driving Scenarios 提出HarmonicNeRF以解决自动驾驶场景中的3D重建问题 3D reconstruction NeRF neural radiance field ✅
6 FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing 提出FLATTEN以解决文本到视频编辑中的一致性问题 optical flow
7 GradientSurf: Gradient-Domain Neural Surface Reconstruction from RGB Video 提出GradientSurf以解决单目RGB视频表面重建问题 scene reconstruction

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
8 A Real-time Method for Inserting Virtual Objects into Neural Radiance Fields 提出实时方法将虚拟物体插入神经辐射场以解决增强现实问题 manipulation NeRF neural radiance field
9 Anyview: Generalizable Indoor 3D Object Detection with Variable Frames 提出AnyView以解决变帧数室内3D物体检测问题 manipulation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗⭐
10 ViCor: Bridging Visual Understanding and Commonsense Reasoning with Large Language Models 提出ViCor以解决视觉常识推理问题 large language model
11 Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation 提出MAGVIT-v2视频标记器以提升视觉生成效果 large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
12 EdVAE: Mitigating Codebook Collapse with Evidential Discrete Variational Autoencoders 提出EdVAE以解决离散变分自编码器中的代码本崩溃问题 VQ-VAE ✅

⬅️ 返回 cs.CV 首页 · 🏠 返回主页