cs.CV（2023-10-02）

📊 共 21 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 🔗3) 支柱九：具身大模型 (Embodied Foundation Models) (5 🔗1) 支柱一：机器人控制 (Robot Control) (3) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗2) 支柱四：生成式动作 (Generative Motion) (2 🔗1) 支柱七：动作重定向 (Motion Retargeting) (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 PC-NeRF: Parent-Child Neural Radiance Fields under Partial Sensor Data Loss in Autonomous Driving Environments 提出PC-NeRF以解决自动驾驶环境中部分传感器数据丢失问题 3D reconstruction NeRF neural radiance field ✅
2 CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction 提出CLIPSelf以解决CLIP在开放词汇密集预测中的区域语言对齐问题 open-vocabulary open vocabulary ✅
3 DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detection 提出DST-Det以解决开放词汇目标检测问题 open-vocabulary open vocabulary ✅
4 Task-guided Domain Gap Reduction for Monocular Depth Prediction in Endoscopy 提出任务引导的领域间差距缩减方法以改善内窥镜单目深度预测 monocular depth
5 Adaptive Visual Scene Understanding: Incremental Scene Graph Generation 提出增量场景图生成方法以解决动态视觉理解问题 scene understanding
6 Segmenting the motion components of a video: A long-term unsupervised model 提出长时间无监督模型以实现视频运动分割 optical flow
7 Multi-task Learning with 3D-Aware Regularization 提出3D感知正则化以解决多任务学习中的噪声问题 depth estimation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
8 DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model 提出DriveGPT4以解决自主驾驶中的可解释性问题 large language model multimodal
9 HyMNet: a Multimodal Deep Learning System for Hypertension Classification using Fundus Photographs and Cardiometabolic Risk Factors 提出HyMNet以解决单一数据源对高血压分类的局限性 foundation model multimodal ✅
10 Less is More: Toward Zero-Shot Local Scene Graph Generation via Foundation Models 提出ELEGANT框架以解决零样本局部场景图生成问题 foundation model
11 Making LLaMA SEE and Draw with SEED Tokenizer 提出SEED图像分词器以解决多模态统一处理问题 large language model multimodal
12 NEUCORE: Neural Concept Reasoning for Composed Image Retrieval 提出NEUCORE以解决复合图像检索问题 multimodal

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
13 Intelligent Knee Sleeves: A Real-time Multimodal Dataset for 3D Lower Body Motion Estimation Using Smart Textile 提出智能膝盖护套以解决3D下肢运动估计问题 locomotion motion estimation multimodal
14 STARS: Zero-shot Sim-to-Real Transfer for Segmentation of Shipwrecks in Sonar Imagery 提出STARS以解决零样本船舶残骸分割问题 sim-to-real
15 Trained Latent Space Navigation to Prevent Lack of Photorealism in Generated Images on Style-based Models 提出无监督方法以解决生成图像缺乏真实感的问题 manipulation

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

#题目一句话要点标签🔗⭐
16 Toward effective protection against diffusion based mimicry through score distillation 提出基于得分蒸馏的策略以有效防护扩散模型的模仿攻击 distillation ✅
17 Strength in Diversity: Multi-Branch Representation Learning for Vehicle Re-Identification 提出轻量级多分支深度架构以提升车辆重识别性能 representation learning ✅
18 Learnable Cross-modal Knowledge Distillation for Multi-modal Learning with Missing Modality 提出可学习的跨模态知识蒸馏以解决多模态学习中的缺失模态问题 distillation

🔬 支柱四：生成式动作 (Generative Motion) (2 篇)

#题目一句话要点标签🔗⭐
19 Reconstructing 3D Human Pose from RGB-D Data with Occlusions 提出新方法以解决RGB-D数据中人体重建的遮挡问题 physically plausible penetration ReMoS
20 Mirror Diffusion Models for Constrained and Watermarked Generation 提出镜面扩散模型以解决约束数据生成问题 MDM ✅

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

#题目一句话要点标签🔗⭐
21 Leveraging Cutting Edge Deep Learning Based Image Matching for Reconstructing a Large Scene from Sparse Images 提出基于深度学习的图像匹配方法以重建稀疏图像的大场景 motion reconstruction

⬅️ 返回 cs.CV 首页 · 🏠 返回主页