# C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From Motion

arXiv: https://arxiv.org/abs/1909.02533 · HTML: https://mlsanity.com/paper/1909.02533/

## Key facts

- Cited by 61 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Sep 2019.

## Built on by (most cited first, 30 of 61)

- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking](https://mlsanity.com/paper/2307.15055/) (2023)
- [Shape of Motion: 4D Reconstruction from a Single Video](https://mlsanity.com/paper/2407.13764/) (2024)
- [Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories](https://mlsanity.com/paper/2204.04153/) (2022)
- [LASR: Learning Articulated Shape Reconstruction from a Monocular Video](https://mlsanity.com/paper/2105.02976/) (2021)
- [RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild](https://mlsanity.com/paper/2208.05963/) (2022)
- [St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World](https://mlsanity.com/paper/2504.13152/) (2025)
- [Multiview Compressive Coding for 3D Reconstruction](https://mlsanity.com/paper/2301.08247/) (2023)
- [DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision](https://mlsanity.com/paper/2105.06464/) (2021)
- [SparsePose: Sparse-View Camera Pose Regression and Refinement](https://mlsanity.com/paper/2211.16991/) (2022)
- [Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects](https://mlsanity.com/paper/2112.11347/) (2021)
- [Estimating Egocentric 3D Human Pose in the Wild with External Weak Supervision](https://mlsanity.com/paper/2201.07929/) (2022)
- [ConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapes](https://mlsanity.com/paper/2201.07788/) (2022)
- [Gravity-Aware Monocular 3D Human-Object Reconstruction](https://mlsanity.com/paper/2108.08844/) (2021)
- [State of the Art in Dense Monocular Non-Rigid 3D Reconstruction](https://mlsanity.com/paper/2210.15664/) (2022)
- [KAMA: 3D Keypoint Aware Body Mesh Articulation](https://mlsanity.com/paper/2104.13502/) (2021)
- [Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation](https://mlsanity.com/paper/2203.15293/) (2022)
- [Unbiased 4D: Monocular 4D Reconstruction with a Neural Deformation Model](https://mlsanity.com/paper/2206.08368/) (2022)
- [φ-SfT: Shape-from-Template with a Physics-Based Deformation Model](https://mlsanity.com/paper/2203.11938/) (2022)
- [To The Point: Correspondence-driven monocular 3D category reconstruction](https://mlsanity.com/paper/2106.05662/) (2021)
- [Learning 3D Object Shape and Layout without 3D Supervision](https://mlsanity.com/paper/2206.07028/) (2022)
- [Shape-Pose Disentanglement using SE(3)-equivariant Vector Neurons](https://mlsanity.com/paper/2204.01159/) (2022)
- [StrobeNet: Category-Level Multiview Reconstruction of Articulated Objects](https://mlsanity.com/paper/2105.08016/) (2021)
- [Fast Encoder-Based 3D from Casual Videos via Point Track Processing](https://mlsanity.com/paper/2404.07097/) (2024)
- [Discovering Relationships between Object Categories via Universal Canonical Maps](https://mlsanity.com/paper/2106.09758/) (2021)
- [MoCaNet: Motion Retargeting in-the-wild via Canonicalization Networks](https://mlsanity.com/paper/2112.10082/) (2021)
- [Self-Supervised 3D Human Pose Estimation with Multiple-View Geometry](https://mlsanity.com/paper/2108.07777/) (2021)
- [PAUL: Procrustean Autoencoder for Unsupervised Lifting](https://mlsanity.com/paper/2103.16773/) (2021)
- [PR-RRN: Pairwise-Regularized Residual-Recursive Networks for Non-rigid Structure-from-Motion](https://mlsanity.com/paper/2108.07506/) (2021)
- [Canonical Fields: Self-Supervised Learning of Pose-Canonicalized Neural Fields](https://mlsanity.com/paper/2212.02493/) (2022)

## Abstract (arXiv)

We propose C3DPO, a method for extracting 3D models of deformable objects from 2D keypoint annotations in unconstrained images. We do so by learning a deep network that reconstructs a 3D object from a single view at a time, accounting for partial occlusions, and explicitly factoring the effects of viewpoint changes and object deformations. In order to achieve this factorization, we introduce a novel regularization technique. We first show that the factorization is successful if, and only if, there exists a certain canonicalization function of the reconstructed shapes. Then, we learn the canonicalization function together with the reconstruction one, which constrains the result to be consistent. We demonstrate state-of-the-art reconstruction results for methods that do not use ground-truth 3D supervision for a number of benchmarks, including Up3D and PASCAL3D+. Source code has been made available at https://github.com/facebookresearch/c3dpo_nrsfm.