# Learning to Refine Human Pose Estimation

arXiv: https://arxiv.org/abs/1804.07909 · HTML: https://mlsanity.com/paper/1804.07909/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Apr 2018.

## Built on by (most cited first, 19 of 19)

- [Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression](https://mlsanity.com/paper/2104.02300/) (2021)
- [SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos](https://mlsanity.com/paper/2112.13715/) (2021)
- [Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective](https://mlsanity.com/paper/2104.11536/) (2021)
- [Human Pose as Compositional Tokens](https://mlsanity.com/paper/2303.11638/) (2023)
- [2D Human Pose Estimation: A Survey](https://mlsanity.com/paper/2204.07370/) (2022)
- [Reconstructing Three-Dimensional Models of Interacting Humans](https://mlsanity.com/paper/2308.01854/) (2023)
- [Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity](https://mlsanity.com/paper/2306.07879/) (2023)
- [Prototype-Driven Structure Synergy Network for Remote Sensing Images Segmentation](https://mlsanity.com/paper/2508.04022/) (2025)
- [Jointformer: Single-Frame Lifting Transformer with Error Prediction and Refinement for 3D Human Pose Estimation](https://mlsanity.com/paper/2208.03704/) (2022)
- [Iterative Greedy Matching for 3D Human Pose Tracking from Multiple Views](https://mlsanity.com/paper/2101.09745/) (2021)
- [Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation](https://mlsanity.com/paper/2303.11180/) (2023)
- [Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Models](https://mlsanity.com/paper/2305.13765/) (2023)
- [Learning Structure-Guided Diffusion Model for 2D Human Pose Estimation](https://mlsanity.com/paper/2306.17074/) (2023)
- [Single Person Pose Estimation: A Survey](https://mlsanity.com/paper/2109.10056/) (2021)
- [Self-Constrained Inference Optimization on Structural Groups for Human Pose Estimation](https://mlsanity.com/paper/2207.02425/) (2022)
- [Pose Splatter: A 3D Gaussian Splatting Model for Quantifying Animal Pose and Appearance](https://mlsanity.com/paper/2505.18342/) (2025)
- [A Global to Local Double Embedding Method for Multi-person Pose Estimation](https://mlsanity.com/paper/2102.07318/) (2021)
- [TransFiner: A Full-Scale Refinement Approach for Multiple Object Tracking](https://mlsanity.com/paper/2207.12967/) (2022)
- [Joint angle based learning to refine kinematic human pose estimation](https://mlsanity.com/paper/2507.11075/) (2025)

## Abstract (arXiv)

Multi-person pose estimation in images and videos is an important yet challenging task with many applications. Despite the large improvements in human pose estimation enabled by the development of convolutional neural networks, there still exist a lot of difficult cases where even the state-of-the-art models fail to correctly localize all body joints. This motivates the need for an additional refinement step that addresses these challenging cases and can be easily applied on top of any existing method. In this work, we introduce a pose refinement network (PoseRefiner) which takes as input both the image and a given pose estimate and learns to directly predict a refined pose by jointly reasoning about the input-output space. In order for the network to learn to refine incorrect body joint predictions, we employ a novel data augmentation scheme for training, where we model "hard" human pose cases. We evaluate our approach on four popular large-scale pose estimation benchmarks such as MPII Single- and Multi-Person Pose Estimation, PoseTrack Pose Estimation, and PoseTrack Pose Tracking, and report systematic improvement over the state of the art.