# Robust 3D Human Motion Reconstruction Via Dynamic Template Construction

arXiv: https://arxiv.org/abs/1801.10434 · HTML: https://mlsanity.com/paper/1801.10434/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jan 2018.

## Built on by (most cited first, 13 of 13)

- [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023)
- [Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis](https://mlsanity.com/paper/2312.16812/) (2023)
- [4K4D: Real-Time 4D View Synthesis at 4K Resolution](https://mlsanity.com/paper/2310.11448/) (2023)
- [A Survey of Non-Rigid 3D Registration](https://mlsanity.com/paper/2203.07858/) (2022)
- [TeTriRF: Temporal Tri-Plane Radiance Fields for Efficient Free-Viewpoint Video](https://mlsanity.com/paper/2312.06713/) (2023)
- [Segment Any 4D Gaussians](https://mlsanity.com/paper/2407.04504/) (2024)
- [PREF: Predictability Regularized Neural Motion Fields](https://mlsanity.com/paper/2209.10691/) (2022)
- [Dynamic 2D Gaussians: Geometrically Accurate Radiance Fields for Dynamic Objects](https://mlsanity.com/paper/2409.14072/) (2024)
- [Modeling Ambient Scene Dynamics for Free-view Synthesis](https://mlsanity.com/paper/2406.09395/) (2024)
- [Relit-NeuLF: Efficient Relighting and Novel View Synthesis via Neural 4D Light Field](https://mlsanity.com/paper/2310.14642/) (2023)
- [Street Gaussians without 3D Object Tracker](https://mlsanity.com/paper/2412.05548/) (2024)
- [SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid 3D Registration](https://mlsanity.com/paper/2405.20188/) (2024)
- [STD-GS: Exploring Frame-Event Interaction for SpatioTemporal-Disentangled Gaussian Splatting to Reconstruct High-Dynamic Scene](https://mlsanity.com/paper/2506.23157/) (2025)

## Abstract (arXiv)

In multi-view human body capture systems, the recovered 3D geometry or even the acquired imagery data can be heavily corrupted due to occlusions, noise, limited field of- view, etc. Direct estimation of 3D pose, body shape or motion on these low-quality data has been traditionally challenging.In this paper, we present a graph-based non-rigid shape registration framework that can simultaneously recover 3D human body geometry and estimate pose/motion at high fidelity.Our approach first generates a global full-body template by registering all poses in the acquired motion sequence.We then construct a deformable graph by utilizing the rigid components in the global template. We directly warp the global template graph back to each motion frame in order to fill in missing geometry. Specifically, we combine local rigidity and temporal coherence constraints to maintain geometry and motion consistencies. Comprehensive experiments on various scenes show that our method is accurate and robust even in the presence of drastic motions.