随笔分类 -  Pose

Human Pose, Hand Pose, Hand Tracking等方面学习
[Paper Reading] Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Driving
摘要：目录Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous DrivingTL;DRMethod算法架构Modality Fusion of LiDAR and CameraAuxiliary Point 阅读全文
posted @ 2024-11-22 21:47 fariver 阅读(16) 评论(0) 推荐(0) 编辑
[PaperReading] EgoPoseFormer: A Simple Baseline for Stereo Egocentric 3D Human Pose Estimation
摘要：目录EgoPoseFormer: A Simple Baseline for Stereo Egocentric 3D Human Pose EstimationTL;DRMethodDeformable Stereo AttentionExperiment效果可视化总结与思考相关链接资料查询 Eg 阅读全文
posted @ 2024-11-22 21:19 fariver 阅读(18) 评论(0) 推荐(0) 编辑
[Paper Reading] Sapiens: Foundation for Human Vision Models
摘要：名称 link 时间：24.08 机构：Meta RealityLabs TL;DR 放出一个human-centric视觉任务的fundation model，该模型在3亿样本(Humans-300M)上进行无监督预训练，实验证明在human-centric视觉任务(2d pose估计/深度估计/ 阅读全文
posted @ 2024-09-04 18:23 fariver 阅读(58) 评论(0) 推荐(0) 编辑
[Paper Reading] Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement
摘要：Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement link 时间：CVPR2024 机构：马普所 & Saarland Informatics Campus & Goo 阅读全文
posted @ 2024-08-23 18:24 fariver 阅读(40) 评论(0) 推荐(0) 编辑
[Paper Reading] HandDiff: 3D Hand Pose Estimation with Diffusion on Image-Point Cloud
摘要：HandDiff: 3D Hand Pose Estimation with Diffusion on Image-Point Cloud HandDiff: 3D Hand Pose Estimation with Diffusion on Image-Point Cloud 时间：CVPR202 阅读全文
posted @ 2024-08-20 21:48 fariver 阅读(43) 评论(0) 推荐(0) 编辑
[Paper Reading] Reconstructing Hands in 3D with Transformers
摘要：名称 Reconstructing Hands in 3D with Transformers 时间：CVPR2024 机构：UC Berkeley, University of Michigan, New York University TL;DR 本文提出一种使用Transformer来做Han 阅读全文
posted @ 2024-08-20 18:00 fariver 阅读(106) 评论(0) 推荐(0) 编辑
[Paper Reading] Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose Estimation
摘要：名称 Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose Estimation 时间：CVPR2024 机构：The University of Tokyo TL;DR 多目3D hand pose estimation数据比较难标注 阅读全文
posted @ 2024-08-16 17:55 fariver 阅读(3) 评论(0) 推荐(0) 编辑
[Paper Reading] Multiple View Geometry Transformers for 3D Human Pose Estimation
摘要：Multiple View Geometry Transformers for 3D Human Pose Estimation link 时间：CVPR2024 机构：University of Toronto && Southeast University && Microsoft Resear 阅读全文
posted @ 2024-08-13 21:35 fariver 阅读(51) 评论(0) 推荐(0) 编辑

点击右上角即可分享
微信分享提示