cs.CV（2024-04-16）

📊 共 34 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) (13 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (11 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (5) 支柱一：机器人控制 (Robot Control) (2 🔗1) 支柱四：生成式动作 (Generative Motion) (1) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱五：交互与反应 (Interaction & Reaction) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (13 篇)

#题目一句话要点标签🔗⭐
1 SRGS: Super-Resolution 3D Gaussian Splatting 提出SRGS框架以解决3D高斯点云超分辨率问题 3D gaussian splatting 3DGS gaussian splatting
2 Gaussian Splatting Decoder for 3D-aware Generative Adversarial Networks 提出高效的3D高分辨率生成对抗网络解码器以解决NeRF渲染挑战 3D gaussian splatting 3DGS gaussian splatting
3 AbsGS: Recovering Fine Details for 3D Gaussian Splatting 提出AbsGS以解决3D Gaussian Splatting中的细节恢复问题 3D gaussian splatting gaussian splatting splatting ✅
4 Plug-and-Play Acceleration of Occupancy Grid-based NeRF Rendering using VDB Grid and Hierarchical Ray Traversal 提出基于VDB网格和分层光线遍历的OG加速方法以提升NeRF渲染效率 NeRF neural radiance field occupancy grid
5 Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes 提出高效的高质量自适应表面重建方法以解决无界场景中的挑战 3D gaussian splatting 3DGS gaussian splatting
6 PyTorchGeoNodes: Enabling Differentiable Shape Programs for 3D Shape Reconstruction 提出PyTorchGeoNodes以解决3D形状重建问题 3D reconstruction gaussian splatting splatting
7 RapidVol: Rapid Reconstruction of 3D Ultrasound Volumes from Sensorless 2D Scans 提出RapidVol以解决2D超声图像重建3D体积问题 3D reconstruction neural radiance field implicit representation
8 CMU-Flownet: Exploring Point Cloud Scene Flow Estimation in Occluded Scenario 提出CMU-Flownet以解决点云场景流估计中的遮挡问题 scene flow
9 PreGSU-A Generalized Traffic Scene Understanding Model for Autonomous Driving based on Pre-trained Graph Attention Network 提出PreGSU以解决自动驾驶场景理解问题 scene understanding
10 Watch Your Step: Optimal Retrieval for Continual Learning at Scale 提出选择性检索策略以优化大规模持续学习 open-vocabulary open vocabulary
11 ECLAIR: A High-Fidelity Aerial LiDAR Dataset for Semantic Segmentation 提出ECLAIR数据集以推动点云语义分割研究 scene understanding
12 CorrespondentDream: Enhancing 3D Fidelity of Text-to-3D using Cross-View Correspondences 提出CorrespondentDream以解决3D几何一致性问题 NeRF
13 1st Place Solution for ICCV 2023 OmniObject3D Challenge: Sparse-View Reconstruction 提出基于Pixel-NeRF的稀疏视图重建方法以解决三维重建问题 NeRF

🔬 支柱二：RL算法与架构 (RL & Architecture) (11 篇)

#题目一句话要点标签🔗⭐
14 HumMUSS: Human Motion Understanding using State Space Models 提出HumMUSS以解决人类动作理解中的实时预测问题 state space model human motion spatiotemporal
15 Dynamic Self-adaptive Multiscale Distillation from Pre-trained Multimodal Large Model for Efficient Cross-modal Representation Learning 提出动态自适应多尺度蒸馏方法以解决多模态表示学习效率问题 representation learning distillation multimodal
16 MK-SGN: A Spiking Graph Convolutional Network with Multimodal Fusion and Knowledge Distillation for Skeleton-based Action Recognition 提出MK-SGN以解决骨架动作识别中的能耗问题 distillation spatial relationship multimodal
17 COMBO: Compositional World Models for Embodied Multi-Agent Cooperation 提出组合世界模型以解决多智能体合作问题 world model world models egocentric ✅
18 Masked Autoencoders for Microscopy are Scalable Learners of Cellular Biology 提出通道无关的自监督学习方法以解决显微镜图像特征提取问题 masked autoencoder MAE foundation model
19 Residual Connections Harm Generative Representation Learning 提出加权因子以提升生成表示学习中的语义特征学习 representation learning masked autoencoder MAE
20 EucliDreamer: Fast and High-Quality Texturing for 3D Models with Depth-Conditioned Stable Diffusion 提出EucliDreamer以解决3D模型纹理生成问题 dreamer distillation
21 Contextrast: Contextual Contrastive Learning for Semantic Segmentation 提出Contextrast以解决语义分割中的上下文关系问题 contrastive learning
22 Robust Noisy Label Learning via Two-Stream Sample Distillation 提出双流样本蒸馏方法以解决噪声标签学习问题 distillation
23 Camera clustering for scalable stream-based active distillation 提出基于相机聚类的高效视频对象检测模型蒸馏方法 distillation
24 Vision-and-Language Navigation via Causal Learning 提出GOAT模型以解决视觉-语言导航中的数据集偏差问题 contrastive learning VLN ✅

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

#题目一句话要点标签🔗⭐
25 Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models 提出Med-MoE以解决医疗多模态任务的轻量化问题 large language model multimodal
26 Multi-Task Multi-Modal Self-Supervised Learning for Facial Expression Recognition 提出多任务多模态自监督学习以提升面部表情识别性能 multimodal
27 From a Lossless (~1.5:1) Compression Algorithm for Llama2 7B Weights to Variable Precision, Variable Range, Compressed Numeric Data Types for CNNs and LLMs 提出一种压缩算法以优化Llama2 7B模型权重存储 large language model
28 Automated Evaluation of Large Vision-Language Models on Self-driving Corner Cases 提出CODA-LM以解决自动评估自驾角落案例的问题 large language model
29 Awareness of uncertainty in classification using a multivariate model and multi-views 提出不确定性感知模型以提升分类任务的准确性 multimodal

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
30 MOWA: Multiple-in-One Image Warping Model 提出MOWA模型以解决多任务图像变形问题 manipulation motion estimation ✅
31 Semantic-Based Active Perception for Humanoid Visual Tasks with Foveal Sensors 提出基于语义的主动感知模型以解决人形机器人视觉任务 humanoid

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
32 Generating Human Interaction Motions in Scenes with Text Control 提出TeSMo以解决文本控制的人类交互动作生成问题 motion diffusion model motion diffusion text-to-motion

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

#题目一句话要点标签🔗⭐
33 MS-MANO: Enabling Hand Pose Tracking with Biomechanical Constraints 提出MS-MANO以解决手势追踪中的生理约束问题 MANO

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
34 Neuromorphic Vision-based Motion Segmentation with Graph Transformer Neural Network 提出基于图变换神经网络的事件驱动运动分割算法 IMoS spatiotemporal

⬅️ 返回 cs.CV 首页 · 🏠 返回主页