The task of 2D animal pose estimation plays a crucial role in advancing deep learning applications in animal behavior analysis and ecological research. Despite notable progress in some existing approaches, our study reveals that the scarcity of high-quality datasets remains a significant bottleneck, limiting the full potential of current methods. To address this challenge, we propose a novel Controllable Image Generation Pipeline for synthesizing animal pose estimation data, termed AP-CAP. Within this pipeline, we introduce a Multi-Modal Animal Image Generation Model capable of producing images with expected poses. To enhance the quality and diversity of the generated data, we further propose three innovative strategies: (1) Modality-Fusion-Based Animal Image Synthesis Strategy to integrate multi-source appearance representations, (2) Pose-Adjustment-Based Animal Image Synthesis Strategy to dynamically capture diverse pose variations, and (3) Caption-Enhancement-Based Animal Image Synthesis Strategy to enrich visual semantic understanding. Leveraging the proposed model and strategies, we create the MPCH Dataset (Modality-Pose-Caption Hybrid), the first hybrid dataset that innovatively combines synthetic and real data, establishing the largest-scale multi-source heterogeneous benchmark repository for animal pose estimation to date. Extensive experiments demonstrate the superiority of our method in improving both the performance and generalization capability of animal pose estimators.
View on arXiv@article{wang2025_2504.00394,
title={ AP-CAP: Advancing High-Quality Data Synthesis for Animal Pose Estimation via a Controllable Image Generation Pipeline },
author={ Lei Wang and Yujie Zhong and Xiaopeng Sun and Jingchun Cheng and Chengjian Feng and Qiong Cao and Lin Ma and Zhaoxin Fan },
journal={arXiv preprint arXiv:2504.00394},
year={ 2025 }
}