MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistency
MixCycle:具有循环一致性的混合辅助半监督 3D 单对象跟踪
Deep Fusion Transformer Network with Weighted Vector-Wise Keypoints Voting for Robust 6D Object Pose Estimation
具有加权矢量关键点投票的深度融合 Transformer 网络,用于稳健的 6D 物体姿态估计
IST-Net: Prior-Free Category-Level Pose Estimation with Implicit Space Transformation
IST-Net:具有隐式空间变换的无先验类别级姿势估计
VI-Net: Boosting Category-Level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representations
VI-Net:通过学习球形表示上的解耦旋转来增强类别级 6D 物体姿态估计
CheckerPose: Progressive Dense Keypoint Localization for Object Pose Estimation with Graph Neural Network
CheckerPose:使用图神经网络进行物体姿态估计的渐进密集关键点定位
SOCS: Semantically-Aware Object Coordinate Space for Category-Level 6D Object Pose Estimation under Large Shape Variations
SOCS:大形状变化下类别级 6D 物体姿态估计的语义感知物体坐标空间
Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimation
自监督 6D 物体姿态估计的伪流一致性
Tracking by 3D Model Estimation of Unknown Objects in Videos
通过 3D 模型估计视频中未知物体进行跟踪
Linear-Covariance Loss for End-to-End Learning of 6D Pose Estimation
6D 姿态估计端到端学习的线性协方差损失
Vanishing Point Estimation in Uncalibrated Images with Prior Gravity Direction
具有先验重力方向的未校准图像中的消失点估计
猜您喜欢
评论