# Lifting by Image -- Leveraging Image Cues for Accurate 3D Human Pose Estimation

arXiv: https://arxiv.org/abs/2312.15636 · HTML: https://mlsanity.com/paper/2312.15636/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 29 references that are in the map.
- First posted on arXiv 25 Dec 2023.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision](https://mlsanity.com/paper/1611.09813/) (2016)
- [3D human pose estimation in video with temporal convolutions and semi-supervised training](https://mlsanity.com/paper/1811.11742/) (2018)
- [A simple yet effective baseline for 3d human pose estimation](https://mlsanity.com/paper/1705.03098/) (2017)
- [Cascaded Pyramid Network for Multi-Person Pose Estimation](https://mlsanity.com/paper/1711.07319/) (2017)
- [Semantic Graph Convolutional Networks for 3D Human Pose Regression](https://mlsanity.com/paper/1904.03345/) (2019)
- [Graph Stacked Hourglass Networks for 3D Human Pose Estimation](https://mlsanity.com/paper/2103.16385/) (2021)
- [Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network](https://mlsanity.com/paper/1904.05547/) (2019)
- [Cascaded deep monocular 3D human pose estimation with evolutionary training data](https://mlsanity.com/paper/2006.07778/) (2020)
- [Feature Boosting Network For 3D Pose Estimation](https://mlsanity.com/paper/1901.04877/) (2019)
- [What Decreases Editing Capability? Domain-Specific Hybrid Refinement for Improved GAN Inversion](https://mlsanity.com/paper/2301.12141/) (2023)
- [Image is All You Need to Empower Large-scale Diffusion Models for In-Domain Generation](https://mlsanity.com/paper/2312.08195/) (2023)
- [DWnet: Deep-Wide Network for 3D Action Recognition](https://mlsanity.com/paper/1908.11036/) (2019)

## Built on by (most cited first, 6 of 6)

- [Controllable Generation with Text-to-Image Diffusion Models: A Survey](https://mlsanity.com/paper/2403.04279/) (2024)
- [Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network](https://mlsanity.com/paper/2408.02922/) (2024)
- [HiPART: Hierarchical Pose AutoRegressive Transformer for Occluded 3D Human Pose Estimation](https://mlsanity.com/paper/2503.23331/) (2025)
- [NanoHTNet: Nano Human Topology Network for Efficient 3D Human Pose Estimation](https://mlsanity.com/paper/2501.15763/) (2025)
- [AugLift: Depth-Aware Input Reparameterization Improves Domain Generalization in 2D-to-3D Pose Lifting](https://mlsanity.com/paper/2508.07112/) (2025)
- [HyperDiff: Hypergraph Guided Diffusion Model for 3D Human Pose Estimation](https://mlsanity.com/paper/2508.14431/) (2025)

## Abstract (arXiv)

The "lifting from 2D pose" method has been the dominant approach to 3D Human Pose Estimation (3DHPE) due to the powerful visual analysis ability of 2D pose estimators. Widely known, there exists a depth ambiguity problem when estimating solely from 2D pose, where one 2D pose can be mapped to multiple 3D poses. Intuitively, the rich semantic and texture information in images can contribute to a more accurate "lifting" procedure. Yet, existing research encounters two primary challenges. Firstly, the distribution of image data in 3D motion capture datasets is too narrow because of the laboratorial environment, which leads to poor generalization ability of methods trained with image information. Secondly, effective strategies for leveraging image information are lacking. In this paper, we give new insight into the cause of poor generalization problems and the effectiveness of image features. Based on that, we propose an advanced framework. Specifically, the framework consists of two stages. First, we enable the keypoints to query and select the beneficial features from all image patches. To reduce the keypoints attention to inconsequential background features, we design a novel Pose-guided Transformer Layer, which adaptively limits the updates to unimportant image patches. Then, through a designed Adaptive Feature Selection Module, we prune less significant image patches from the feature map. In the second stage, we allow the keypoints to further emphasize the retained critical image features. This progressive learning approach prevents further training on insignificant image features. Experimental results show that our model achieves state-of-the-art performance on both the Human3.6M dataset and the MPI-INF-3DHP dataset.