# Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimation

arXiv: https://arxiv.org/abs/2004.03686 · HTML: https://mlsanity.com/paper/2004.03686/

## Key facts

- Cited by 113 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2020.

## Built on by (most cited first, 30 of 113)

- [Humans in 4D: Reconstructing and Tracking Humans with Transformers](https://mlsanity.com/paper/2305.20091/) (2023)
- [PARE: Part Attention Regressor for 3D Human Body Estimation](https://mlsanity.com/paper/2104.08527/) (2021)
- [CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation](https://mlsanity.com/paper/2208.00571/) (2022)
- [BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion](https://mlsanity.com/paper/2306.16940/) (2023)
- [AGORA: Avatars in Geography Optimized for Regression Analysis](https://mlsanity.com/paper/2104.14643/) (2021)
- [MotionBERT: A Unified Perspective on Learning Human Motion Representations](https://mlsanity.com/paper/2210.06551/) (2022)
- [ARCH++: Animation-Ready Clothed Human Reconstruction Revisited](https://mlsanity.com/paper/2108.07845/) (2021)
- [FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration](https://mlsanity.com/paper/2108.06428/) (2021)
- [SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation](https://mlsanity.com/paper/2309.17448/) (2023)
- [Putting People in their Place: Monocular Regression of 3D People in Depth](https://mlsanity.com/paper/2112.08274/) (2021)
- [Decoupling Human and Camera Motion from Videos in the Wild](https://mlsanity.com/paper/2302.12827/) (2023)
- [Collaborative Regression of Expressive Bodies using Moderation](https://mlsanity.com/paper/2105.05301/) (2021)
- [SPEC: Seeing People in the Wild with an Estimated Camera](https://mlsanity.com/paper/2110.00620/) (2021)
- [Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation](https://mlsanity.com/paper/2303.07937/) (2023)
- [One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer](https://mlsanity.com/paper/2303.16160/) (2023)
- [TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos](https://mlsanity.com/paper/2403.17346/) (2024)
- [Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer](https://mlsanity.com/paper/2204.08680/) (2022)
- [Hi4D: 4D Instance Segmentation of Close Human Interaction](https://mlsanity.com/paper/2303.15380/) (2023)
- [Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes](https://mlsanity.com/paper/2303.02760/) (2023)
- [CameraHMR: Aligning People with Perspective](https://mlsanity.com/paper/2411.08128/) (2024)
- [SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos](https://mlsanity.com/paper/2112.13715/) (2021)
- [Estimating Body and Hand Motion in an Ego-sensed World](https://mlsanity.com/paper/2410.03665/) (2024)
- [Occluded Human Mesh Recovery](https://mlsanity.com/paper/2203.13349/) (2022)
- [Accurate 3D Body Shape Regression using Metric and Semantic Attributes](https://mlsanity.com/paper/2206.07036/) (2022)
- [Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats](https://mlsanity.com/paper/2212.14474/) (2022)
- [HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery](https://mlsanity.com/paper/2304.05690/) (2023)
- [ReFit: Recurrent Fitting Network for 3D Human Recovery](https://mlsanity.com/paper/2308.11184/) (2023)
- [NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2305.08590/) (2023)
- [Generative Proxemics: A Prior for 3D Social Interaction from Images](https://mlsanity.com/paper/2306.09337/) (2023)
- [D&D: Learning Human Dynamics from Dynamic Camera](https://mlsanity.com/paper/2209.08790/) (2022)

## Abstract (arXiv)

Differently from 2D image datasets such as COCO, large-scale human datasets with 3D ground-truth annotations are very difficult to obtain in the wild. In this paper, we address this problem by augmenting existing 2D datasets with high-quality 3D pose fits. Remarkably, the resulting annotations are sufficient to train from scratch 3D pose regressor networks that outperform the current state-of-the-art on in-the-wild benchmarks such as 3DPW. Additionally, training on our augmented data is straightforward as it does not require to mix multiple and incompatible 2D and 3D datasets or to use complicated network architectures and training procedures. This simplified pipeline affords additional improvements, including injecting extreme crop augmentations to better reconstruct highly truncated people, and incorporating auxiliary inputs to improve 3D pose estimation accuracy. It also reduces the dependency on 3D datasets such as H36M that have restrictive licenses. We also use our method to introduce new benchmarks for the study of real-world challenges such as occlusions, truncations, and rare body poses. In order to obtain such high quality 3D pseudo-annotations, inspired by progress in internal learning, we introduce Exemplar Fine-Tuning (EFT). EFT combines the re-projection accuracy of fitting methods like SMPLify with a 3D pose prior implicitly captured by a pre-trained 3D pose regressor network. We show that EFT produces 3D annotations that result in better downstream performance and are qualitatively preferable in an extensive human-based assessment.