SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2507.10437 · 2025

4D-Animal: Freely Reconstructing Animatable 3D Animals from Videos

Zhongzhan Huang, Alan Yuille, Shanshan Zhong, Wufei Ma, Qihao Liu, Guofeng Zhang, Jieneng Chen, Jiawei Peng, Zehan Zheng

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Abstract

Existing methods for reconstructing animatable 3D animals from videos typically rely on sparse semantic keypoints to fit parametric models. However, obtaining such keypoints is labor-intensive, and keypoint detectors trained on limited animal data are often unreliable. To address this, we propose 4D-Animal, a novel framework that reconstructs animatable 3D animals from videos without requiring sparse keypoint annotations. Our approach introduces a dense feature network that maps 2D representations to SMAL parameters, enhancing both the efficiency and stability of the fitting process. Furthermore, we develop a hierarchical alignment strategy that integrates silhouette, part-level, pixel-level, and temporal cues from pre-trained 2D visual models to produce accurate and temporally coherent reconstructions across frames. Extensive experiments demonstrate that 4D-Animal outperforms both model-based and model-free baselines. Moreover, the high-quality 3D assets generated by our method can benefit other 3D tasks, underscoring its potential for large-scale applications. The code is released at https://github.com/zhongshsh/4D-Animal.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2507.10437")
get_code_for_paper("2507.10437")
have("2507.10437")

Connect an agent — have() is free.