Lune

CVPR2024Top-tier venue

HardMo: A Large-Scale Hardcase Dataset for Motion Capture

Jiaqi Liao, Chuanchen Luo, Yinuo Du, Yuxi Wang, Xucheng Yin, Man Zhang, Zhaoxiang Zhang, Junran Peng

Abstract

a) (b) (c) (a) (b) (c) Figure 1. Comparisons between vanilla 4DHumans [10] and our HardMo-4DHumans. The teaser comprises four sub-figures. Each subfigure, from left to right, corresponds to (a) the input image, (b) the prediction of HardMo-4DHumans, and (c) the prediction of vanilla 4DHumans. In comparison, our HardMo-4DHumans is superior in the alignment of hand and foot posture.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Humans in 4D: Reconstructing and Tracking Humans with Transformers cites PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop
  • Humans in 4D: Reconstructing and Tracking Humans with Transformers cites Learning to Reconstruct 3D Human Pose and Shape via Model-Fitting in the Loop
  • Humans in 4D: Reconstructing and Tracking Humans with Transformers cites HuMoR: 3D Human Motion Model for Robust Pose Estimation
  • Humans in 4D: Reconstructing and Tracking Humans with Transformers cites Probabilistic Modeling for Human Mesh Recovery
  • PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop cites Learning to Reconstruct 3D Human Pose and Shape via Model-Fitting in the Loop
  • HuMoR: 3D Human Motion Model for Robust Pose Estimation cites Learning to Reconstruct 3D Human Pose and Shape via Model-Fitting in the Loop
  • Probabilistic Modeling for Human Mesh Recovery cites Learning to Reconstruct 3D Human Pose and Shape via Model-Fitting in the Loop
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on12

  1. Learning to Reconstruct 3D Human Pose and Shape via Model-Fitting in the LoopNikos Kolotouros, Georgios Pavlakos, Michael J. Black, Kostas DaniilidisICCV 2019 · 1,139 citations
  2. HuMoR: 3D Human Motion Model for Robust Pose EstimationDavis Rempe, Tolga Birdal, Aaron Hertzmann, Jimei Yang et al.ICCV 2021 · 398 citations
  3. Humans in 4D: Reconstructing and Tracking Humans with TransformersShubham Goel, Georgios Pavlakos, Jathushan Rajasegaran, Angjoo Kanazawa et al.ICCV 2023 · 390 citations
  4. PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback LoopHongwen Zhang, Yating Tian, Xinchi Zhou, Wanli Ouyang et al.ICCV 2021 · 376 citations
  5. Probabilistic Modeling for Human Mesh RecoveryNikos Kolotouros, Georgios Pavlakos, Dinesh Jayaraman, Kostas DaniilidisICCV 2021 · 201 citations

Related papers

  1. Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic CameraZhengdi Yu, Stefanos Zafeiriou, Tolga BirdalCVPR 2025
  2. SurMo: Surface-based 4D Motion Modeling for Dynamic Human RenderingTao Hu, Fangzhou Hong, Ziwei LiuCVPR 2024
  3. CLOTH4D: A Dataset for Clothed Human ReconstructionXingxing Zou, Xintong Han, Waikeung WongCVPR 2023
  4. MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human ReconstructionGangjian Zhang, Nanjie Yao, Shunsi Zhang, Hanfeng Zhao et al.CVPR 2025
  5. MobileH2R: Learning Generalizable Human to Mobile Robot Handover Exclusively from Scalable and Diverse Synthetic DataZifan Wang, Ziqing Chen, Junyu Chen, Jilong Wang et al.CVPR 2025
Dusk over the sea between two cliffs drawn in fine vertical lines