# Canonical Pose Reconstruction from Single Depth Image for 3D Non-rigid Pose Recovery on Limited Datasets

arXiv: https://arxiv.org/abs/2505.17992 · HTML: https://mlsanity.com/paper/2505.17992/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 27 references that are in the map.
- First posted on arXiv 23 May 2025.

## Builds on (most cited first, 6 of 6)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion](https://mlsanity.com/paper/2003.01456/) (2020)
- [ShapeFormer: Transformer-based Shape Completion via Sparse Representation](https://mlsanity.com/paper/2201.10326/) (2022)
- [Dense 3D Object Reconstruction from a Single Depth View](https://mlsanity.com/paper/1802.00411/) (2018)
- [Shape retrieval of non-rigid 3d human models](https://mlsanity.com/paper/2003.08763/) (2020)

## Abstract (arXiv)

3D reconstruction from 2D inputs, especially for non-rigid objects like humans, presents unique challenges due to the significant range of possible deformations. Traditional methods often struggle with non-rigid shapes, which require extensive training data to cover the entire deformation space. This study addresses these limitations by proposing a canonical pose reconstruction model that transforms single-view depth images of deformable shapes into a canonical form. This alignment facilitates shape reconstruction by enabling the application of rigid object reconstruction techniques, and supports recovering the input pose in voxel representation as part of the reconstruction task, utilizing both the original and deformed depth images. Notably, our model achieves effective results with only a small dataset of approximately 300 samples. Experimental results on animal and human datasets demonstrate that our model outperforms other state-of-the-art methods.