# V-VIPE: Variational View Invariant Pose Embedding

arXiv: https://arxiv.org/abs/2407.07092 · HTML: https://mlsanity.com/paper/2407.07092/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 34 references that are in the map.
- First posted on arXiv 9 Jul 2024.

## Builds on (most cited first, 23 of 23)

- [Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision](https://mlsanity.com/paper/1611.09813/) (2016)
- [Cascaded Pyramid Network for Multi-Person Pose Estimation](https://mlsanity.com/paper/1711.07319/) (2017)
- [RMPE: Regional Multi-person Pose Estimation](https://mlsanity.com/paper/1612.00137/) (2016)
- [HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2011.14672/) (2020)
- [3D Human Pose Estimation with Spatial and Temporal Transformers](https://mlsanity.com/paper/2103.10455/) (2021)
- [Integral Human Pose Regression](https://mlsanity.com/paper/1711.08229/) (2017)
- [Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose](https://mlsanity.com/paper/1611.07828/) (2016)
- [CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark](https://mlsanity.com/paper/1812.00324/) (2018)
- [Learning a Predictable and Generative Vector Representation for Objects](https://mlsanity.com/paper/1603.08637/) (2016)
- [Self-Supervised Learning of 3D Human Pose using Multi-view Geometry](https://mlsanity.com/paper/1903.02330/) (2019)
- [Unsupervised 3D Pose Estimation with Geometric Self-Supervision](https://mlsanity.com/paper/1904.04812/) (2019)
- [SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach](https://mlsanity.com/paper/2007.09389/) (2020)
- [3D Human Pose Estimation in the Wild by Adversarial Learning](https://mlsanity.com/paper/1803.09722/) (2018)
- [Pose Flow: Efficient Online Pose Tracking](https://mlsanity.com/paper/1802.00977/) (2018)
- [Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking](https://mlsanity.com/paper/1904.01324/) (2019)
- [Direct Multi-view Multi-person 3D Pose Estimation](https://mlsanity.com/paper/2111.04076/) (2021)
- [Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation](https://mlsanity.com/paper/2004.02186/) (2020)
- [3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training](https://mlsanity.com/paper/2004.11822/) (2020)
- [View-Invariant Probabilistic Embedding for Human Pose](https://mlsanity.com/paper/1912.01001/) (2019)
- [TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2110.09554/) (2021)
- [3D Human Pose Estimation Using Convolutional Neural Networks with 2D Pose Information](https://mlsanity.com/paper/1608.03075/) (2016)
- [View Invariant 3D Human Pose Estimation](https://mlsanity.com/paper/1901.10841/) (2019)
- [Learning Pose Grammar to Encode Human Body Configuration for 3D Pose Estimation](https://mlsanity.com/paper/1710.06513/) (2017)

## Built on by (most cited first, 3 of 3)

- [A Study on Real-time Object Detection using Deep Learning](https://mlsanity.com/paper/2602.15926/) (2026)
- [GenCape: Structure-Inductive Generative Modeling for Category-Agnostic Pose Estimation](https://mlsanity.com/paper/2605.13151/) (2026)
- [A Plug-and-Play 2D Motion Interface for Real-World Motion Language Models](https://mlsanity.com/paper/2608.15984/) (2026)

## Abstract (arXiv)

Learning to represent three dimensional (3D) human pose given a two dimensional (2D) image of a person, is a challenging problem. In order to make the problem less ambiguous it has become common practice to estimate 3D pose in the camera coordinate space. However, this makes the task of comparing two 3D poses difficult. In this paper, we address this challenge by separating the problem of estimating 3D pose from 2D images into two steps. We use a variational autoencoder (VAE) to find an embedding that represents 3D poses in canonical coordinate space. We refer to this embedding as variational view-invariant pose embedding V-VIPE. Using V-VIPE we can encode 2D and 3D poses and use the embedding for downstream tasks, like retrieval and classification. We can estimate 3D poses from these embeddings using the decoder as well as generate unseen 3D poses. The variability of our encoding allows it to generalize well to unseen camera views when mapping from 2D space. To the best of our knowledge, V-VIPE is the only representation to offer this diversity of applications. Code and more information can be found at https://v-vipe.github.io/.