# Learning from Synthetic Animals

arXiv: https://arxiv.org/abs/1912.08265 · HTML: https://mlsanity.com/paper/1912.08265/

## Key facts

- Cited by 65 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Dec 2019.

## Built on by (most cited first, 30 of 65)

- [Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding](https://mlsanity.com/paper/2204.08129/) (2022)
- [OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association](https://mlsanity.com/paper/2103.02440/) (2021)
- [BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information](https://mlsanity.com/paper/2203.15536/) (2022)
- [From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation](https://mlsanity.com/paper/2103.14843/) (2021)
- [Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape](https://mlsanity.com/paper/2308.11737/) (2023)
- [MammalNet: A Large-scale Video Benchmark for Mammal Recognition and Behavior Understanding](https://mlsanity.com/paper/2306.00576/) (2023)
- [Estimating Egocentric 3D Human Pose in the Wild with External Weak Supervision](https://mlsanity.com/paper/2201.07929/) (2022)
- [Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation](https://mlsanity.com/paper/2203.15293/) (2022)
- [CLAMP: Prompt-based Contrastive Learning for Connecting Language and Animal Pose](https://mlsanity.com/paper/2206.11752/) (2022)
- [When Pigs Fly: Contextual Reasoning in Synthetic and Natural Scenes](https://mlsanity.com/paper/2104.02215/) (2021)
- [A Unified Framework for Domain Adaptive Pose Estimation](https://mlsanity.com/paper/2204.00172/) (2022)
- [AniMer: Animal Pose and Shape Estimation Using Family Aware Transformer](https://mlsanity.com/paper/2412.00837/) (2024)
- [Learning Part Segmentation through Unsupervised Domain Adaptation from Synthetic Vehicles](https://mlsanity.com/paper/2103.14098/) (2021)
- [Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose](https://mlsanity.com/paper/2110.14213/) (2021)
- [Source-free Domain Adaptive Human Pose Estimation](https://mlsanity.com/paper/2308.03202/) (2023)
- [ScarceNet: Animal Pose Estimation with Scarce Annotations](https://mlsanity.com/paper/2303.15023/) (2023)
- [Prior-guided Source-free Domain Adaptation for Human Pose Estimation](https://mlsanity.com/paper/2308.13954/) (2023)
- [Generative Zoo](https://mlsanity.com/paper/2412.08101/) (2024)
- [A Kinematic Bottleneck Approach For Pose Regression of Flexible Surgical Instruments directly from Images](https://mlsanity.com/paper/2103.00586/) (2021)
- [Progressive Transformation Learning for Leveraging Virtual Images in Training](https://mlsanity.com/paper/2211.01778/) (2022)
- [Designing a Hybrid Neural System to Learn Real-world Crack Segmentation from Fractal-based Simulation](https://mlsanity.com/paper/2309.09637/) (2023)
- [Synthetic Data as Validation](https://mlsanity.com/paper/2310.16052/) (2023)
- [SyDog: A Synthetic Dog Dataset for Improved 2D Pose Estimation](https://mlsanity.com/paper/2108.00249/) (2021)
- [Anatomy-guided domain adaptation for 3D in-bed human pose estimation](https://mlsanity.com/paper/2211.12193/) (2022)
- [Deep Virtual Markers for Articulated 3D Shapes](https://mlsanity.com/paper/2108.09000/) (2021)
- [Domain-Adaptive 2D Human Pose Estimation via Dual Teachers in Extremely Low-Light Conditions](https://mlsanity.com/paper/2407.15451/) (2024)
- [Dessie: Disentanglement for Articulated 3D Horse Shape and Pose Estimation from Images](https://mlsanity.com/paper/2410.03438/) (2024)
- [AniMer+: Unified Pose and Shape Estimation Across Mammalia and Aves via Family-Aware Transformer](https://mlsanity.com/paper/2508.00298/) (2025)
- [Prior-Aware Synthetic Data to the Rescue: Animal Pose Estimation with Very Limited Real Data](https://mlsanity.com/paper/2208.13944/) (2022)
- [Synthetic Data-based Detection of Zebras in Drone Imagery](https://mlsanity.com/paper/2305.00432/) (2023)

## Abstract (arXiv)

Despite great success in human parsing, progress for parsing other deformable articulated objects, like animals, is still limited by the lack of labeled data. In this paper, we use synthetic images and ground truth generated from CAD animal models to address this challenge. To bridge the domain gap between real and synthetic images, we propose a novel consistency-constrained semi-supervised learning method (CC-SSL). Our method leverages both spatial and temporal consistencies, to bootstrap weak models trained on synthetic data with unlabeled real images. We demonstrate the effectiveness of our method on highly deformable animals, such as horses and tigers. Without using any real image label, our method allows for accurate keypoint prediction on real images. Moreover, we quantitatively show that models using synthetic data achieve better generalization performance than models trained on real images across different domains in the Visual Domain Adaptation Challenge dataset. Our synthetic dataset contains 10+ animals with diverse poses and rich ground truth, which enables us to use the multi-task learning strategy to further boost models' performance.