# X as Supervision: Contending with Depth Ambiguity in Unsupervised Monocular 3D Pose Estimation

arXiv: https://arxiv.org/abs/2411.13026 · HTML: https://mlsanity.com/paper/2411.13026/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 40 of its 53 references that are in the map.
- First posted on arXiv 20 Nov 2024.

## Builds on (most cited first, 30 of 40)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision](https://mlsanity.com/paper/1611.09813/) (2016)
- [Learning from Synthetic Humans](https://mlsanity.com/paper/1701.01370/) (2017)
- [3D Menagerie: Modeling the 3D shape and pose of animals](https://mlsanity.com/paper/1611.07700/) (2016)
- [Integral Human Pose Regression](https://mlsanity.com/paper/1711.08229/) (2017)
- [Learning to Estimate 3D Human Pose and Shape from a Single Color Image](https://mlsanity.com/paper/1805.04092/) (2018)
- [Perpetual Humanoid Control for Real-time Simulated Avatars](https://mlsanity.com/paper/2305.06456/) (2023)
- [AGORA: Avatars in Geography Optimized for Regression Analysis](https://mlsanity.com/paper/2104.14643/) (2021)
- [MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2111.12707/) (2021)
- [Unsupervised Learning of Disentangled Representations from Video](https://mlsanity.com/paper/1705.10915/) (2017)
- [Expressive Whole-Body Control for Humanoid Robots](https://mlsanity.com/paper/2402.16796/) (2024)
- [Human Pose Regression with Residual Log-likelihood Estimation](https://mlsanity.com/paper/2107.11291/) (2021)
- [Unsupervised Learning of Object Landmarks through Conditional Image Generation](https://mlsanity.com/paper/1806.07823/) (2018)
- [Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild](https://mlsanity.com/paper/2009.10013/) (2020)
- [Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop](https://mlsanity.com/paper/2007.11110/) (2020)
- [Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning](https://mlsanity.com/paper/1807.03146/) (2018)
- [Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles](https://mlsanity.com/paper/1606.07839/) (2016)
- [Unsupervised Discovery of Object Landmarks as Structural Representations](https://mlsanity.com/paper/1804.04412/) (2018)
- [CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild](https://mlsanity.com/paper/2011.14679/) (2020)
- [SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling](https://mlsanity.com/paper/2303.17368/) (2023)
- [BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information](https://mlsanity.com/paper/2203.15536/) (2022)
- [Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis](https://mlsanity.com/paper/2004.04400/) (2020)
- [Kinematic-Structure-Preserved Representation for Unsupervised 3D Human Pose Estimation](https://mlsanity.com/paper/2006.14107/) (2020)
- [Unsupervised Human Pose Estimation through Transforming Shape Templates](https://mlsanity.com/paper/2105.04154/) (2021)

## Abstract (arXiv)

Recent unsupervised methods for monocular 3D pose estimation have endeavored to reduce dependence on limited annotated 3D data, but most are solely formulated in 2D space, overlooking the inherent depth ambiguity issue. Due to the information loss in 3D-to-2D projection, multiple potential depths may exist, yet only some of them are plausible in human structure. To tackle depth ambiguity, we propose a novel unsupervised framework featuring a multi-hypothesis detector and multiple tailored pretext tasks. The detector extracts multiple hypotheses from a heatmap within a local window, effectively managing the multi-solution problem. Furthermore, the pretext tasks harness 3D human priors from the SMPL model to regularize the solution space of pose estimation, aligning it with the empirical distribution of 3D human structures. This regularization is partially achieved through a GCN-based discriminator within the discriminative learning, and is further complemented with synthetic images through rendering, ensuring plausible estimations. Consequently, our approach demonstrates state-of-the-art unsupervised 3D pose estimation performance on various human datasets. Further evaluations on data scale-up and one animal dataset highlight its generalization capabilities. Code will be available at https://github.com/Charrrrrlie/X-as-Supervision.