# Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose

arXiv: https://arxiv.org/abs/1611.07828 · HTML: https://mlsanity.com/paper/1611.07828/

## Key facts

- Cited by 221 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2016.

## Built on by (most cited first, 30 of 221)

- [PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop](https://mlsanity.com/paper/2103.16507/) (2021)
- [A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose](https://mlsanity.com/paper/2102.06199/) (2021)
- [MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video](https://mlsanity.com/paper/2203.00859/) (2022)
- [Probabilistic Modeling for Human Mesh Recovery](https://mlsanity.com/paper/2108.11944/) (2021)
- [PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images](https://mlsanity.com/paper/2207.06400/) (2022)
- [MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2111.12707/) (2021)
- [StyleGAN-Human: A Data-Centric Odyssey of Human Generation](https://mlsanity.com/paper/2204.11823/) (2022)
- [Collaborative Regression of Expressive Bodies using Moderation](https://mlsanity.com/paper/2105.05301/) (2021)
- [Human Pose Regression with Residual Log-likelihood Estimation](https://mlsanity.com/paper/2107.11291/) (2021)
- [Recovering 3D Human Mesh from Monocular Images: A Survey](https://mlsanity.com/paper/2203.01923/) (2022)
- [DiffPose: Toward More Reliable 3D Pose Estimation](https://mlsanity.com/paper/2211.16940/) (2022)
- [Graph Stacked Hourglass Networks for 3D Human Pose Estimation](https://mlsanity.com/paper/2103.16385/) (2021)
- [Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2103.14304/) (2021)
- [Ego-Body Pose Estimation via Ego-Head Pose Estimation](https://mlsanity.com/paper/2212.04636/) (2022)
- [Neural Monocular 3D Human Motion Capture with Physical Awareness](https://mlsanity.com/paper/2105.01057/) (2021)
- [MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network](https://mlsanity.com/paper/2310.16288/) (2023)
- [Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registration](https://mlsanity.com/paper/2103.02845/) (2021)
- [AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstruction](https://mlsanity.com/paper/2207.12909/) (2022)
- [Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2407.07532/) (2024)
- [Conditional Directed Graph Convolution for 3D Human Pose Estimation](https://mlsanity.com/paper/2107.07797/) (2021)
- [Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective](https://mlsanity.com/paper/2104.11536/) (2021)
- [gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstruction](https://mlsanity.com/paper/2304.11970/) (2023)
- [HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery](https://mlsanity.com/paper/2304.05690/) (2023)
- [Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2303.14747/) (2023)
- [GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video](https://mlsanity.com/paper/2307.05853/) (2023)
- [Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning](https://mlsanity.com/paper/2305.18499/) (2023)
- [Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape](https://mlsanity.com/paper/2308.11737/) (2023)
- [D&D: Learning Human Dynamics from Dynamic Camera](https://mlsanity.com/paper/2209.08790/) (2022)
- [Learning to Regress Bodies from Images using Differentiable Semantic Rendering](https://mlsanity.com/paper/2110.03480/) (2021)
- [Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images](https://mlsanity.com/paper/2109.05885/) (2021)

## Abstract (arXiv)

This paper addresses the challenge of 3D human pose estimation from a single color image. Despite the general success of the end-to-end learning paradigm, top performing approaches employ a two-step solution consisting of a Convolutional Network (ConvNet) for 2D joint localization and a subsequent optimization step to recover 3D pose. In this paper, we identify the representation of 3D pose as a critical issue with current ConvNet approaches and make two important contributions towards validating the value of end-to-end learning for this task. First, we propose a fine discretization of the 3D space around the subject and train a ConvNet to predict per voxel likelihoods for each joint. This creates a natural representation for 3D pose and greatly improves performance over the direct regression of joint coordinates. Second, to further improve upon initial estimates, we employ a coarse-to-fine prediction scheme. This step addresses the large dimensionality increase and enables iterative refinement and repeated processing of the image features. The proposed approach outperforms all state-of-the-art methods on standard benchmarks achieving a relative error reduction greater than 30% on average. Additionally, we investigate using our volumetric representation in a related architecture which is suboptimal compared to our end-to-end approach, but is of practical interest, since it enables training when no image with corresponding 3D groundtruth is available, and allows us to present compelling results for in-the-wild images.