PRIMA: Boosting Animal Mesh Recovery with Biological Priors and Test-Time Adaptation
2026-06-01 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors created PRIMA, a new method to better reconstruct 3D shapes of four-legged animals, especially when there are few examples of some species or rare poses. They use biological knowledge from BioCLIP to improve shape predictions and introduce a way to refine results during testing using 2D images and keypoints. They also built a large dataset called Quadruped3D with diverse animal shapes and poses to train their model. Their approach outperforms previous methods, particularly on less common animals and difficult poses.
3D mesh reconstructionquadruped animalspose estimationspecies imbalanceBioCLIP embeddingstest-time adaptationSMAL modelpseudo-3D annotationskeypoint guidancedataset augmentation
Authors
Xiaohang Yu, Ti Wang, Mackenzie Weygandt Mathis
Abstract
We present PRIMA (*PRI*ors for *M*esh *A*daptation), a framework for robust 3D quadruped mesh recovery under severe species and pose imbalance. Existing animal reconstruction methods often regress toward mean shapes and poses due to limited 3D supervision and long-tailed species distributions, resulting in poor generalization to underrepresented animals and rare articulations. PRIMA addresses this challenge through three key contributions. First, we incorporate BioCLIP embeddings as biological priors to inject semantic and morphological knowledge into the reconstruction process, enabling more accurate and generalizable shape prediction across diverse quadrupeds. Second, we introduce a test-time adaptation (TTA) strategy that refines SMAL predictions using 2D reprojection constraints together with auxiliary keypoint guidance, improving pose and shape estimation while enabling the generation of high-quality pseudo-3D annotations from existing 2D datasets. Third, leveraging this TTA framework, we construct Quadruped3D, a large-scale pseudo-3D dataset that covers diverse species and pose variations to systematically improve model performance. Extensive experiments on Animal3D, CtrlAni3D, Quadruped2D, and Animal Kingdom demonstrate that PRIMA achieves state-of-the-art results, with particularly strong improvements on underrepresented species and challenging poses. Our results highlight the importance of biological priors and adaptation-driven data expansion for scalable and generalizable animal mesh recovery. Code is available at https://github.com/AdaptiveMotorControlLab/PRIMA.