Generalized Few-Shot Point Cloud Segmentation via Geometric Words
通过几何词进行广义少样本点云分割
Boosting 3-DoF Ground-to-Satellite Camera Localization Accuracy via Geometry-Guided Cross-View Transformer
通过几何引导交叉视图变换器提高 3 自由度地对卫星相机定位精度
EP2P-Loc: End-to-End 3D Point to 2D Pixel Localization for Large-Scale Visual Localization
EP2P-Loc:用于大规模视觉定位的端到端 3D 点到 2D 像素定位
Multi-Task View Synthesis with Neural Radiance Fields
具有神经辐射场的多任务视图合成
Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open World
用于开放世界中细粒度场景图生成的视觉提示语言模型
CMDA: Cross-Modality Domain Adaptation for Nighttime Semantic Segmentation
CMDA:夜间语义分割的跨模态域适应
VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answering
VQA-GNN:通过图神经网络利用多模态知识进行推理,实现视觉问答
Disentangle then Parse: Night-Time Semantic Segmentation with Illumination Disentanglement
解开然后解析:夜间语义分割与照明解开
Agglomerative Transformer for Human-Object Interaction Detection
用于人与物体交互检测的凝聚变压器
3D Neural Embedding Likelihood: Probabilistic Inverse Graphics for Robust 6D Pose Estimation
3D 神经嵌入似然:用于鲁棒 6D 姿势估计的概率逆图形
HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation
HiLo:利用高低频关系实现无偏全景场景图生成
RLIPv2: Fast Scaling of Relational Language-Image Pre-Training
RLIPv2:关系语言图像预训练的快速扩展
UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase
UniSeg:统一的多模态 LiDAR 分割网络和 OpenPCSeg 代码库
See more and Know More: Zero-Shot Point Cloud Segmentation via Multi-Modal Visual Data
查看更多并了解更多:通过多模态视觉数据进行零射击点云分割
Compositional Feature Augmentation for Unbiased Scene Graph Generation
用于无偏场景图生成的组合特征增强
CLIPTER: Looking at the Bigger Picture in Scene Text Recognition
CLIPTER:纵观场景文本识别的大局
Towards Models that Can See and Read
迈向能够看到和阅读的模型
SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving
SurroundOcc:自动驾驶的多摄像头 3D 占用预测
DDP: Diffusion Model for Dense Visual Prediction
DDP:密集视觉预测的扩散模型
Understanding 3D Object Interaction from a Single Image
从单个图像了解 3D 对象交互
ObjectSDF++: Improved Object-Compositional Neural Implicit Surfaces
ObjectSDF++:改进的对象组合神经隐式表面
Improving Equivariance in State-of-the-Art Supervised Depth and Normal Predictors
改善最先进的监督深度和正态预测变量的等方差
Semantic Attention Flow Fields for Monocular Dynamic Scene Decomposition
单目动态场景分解的语义注意流场
Holistic Geometric Feature Learning for Structured Reconstruction
用于结构化重建的整体几何特征学习
Scalable Multi-Temporal Remote Sensing Change Data Generation via Simulating Stochastic Change Process
通过模拟随机变化过程生成可扩展的多时相遥感变化数据
TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts
TaskExpert:使用纪念混合专家动态组装多任务表示
STEERER: Resolving Scale Variations for Counting and Localization via Selective Inheritance Learning
STEERER:通过选择性继承学习解决计数和定位的尺度变化
Object-Aware Gaze Target Detection
对象感知注视目标检测
Vision Relation Transformer for Unbiased Scene Graph Generation
用于无偏场景图生成的视觉关系转换器
DQS3D: Densely-Matched Quantization-Aware Semi-Supervised 3D Detection
DQS3D:密集匹配量化感知半监督 3D 检测
Shape Anchor Guided Holistic Indoor Scene Understanding
形状锚引导整体室内场景理解
SGAligner: 3D Scene Alignment with Scene Graphs
SGAligner:使用场景图进行 3D 场景对齐
Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance Segmentation
被字幕背叛:开放词汇实例分割的联合字幕基础和生成
猜您喜欢
推荐内容
开源项目推荐 更多
热门活动
热门器件
用户搜过
随便看看
热门下载
热门文章
热门标签
评论