Aug 1, 2025 · To address these limitations, we introduce AniMer+, an extended version of our scalable AniMer framework. In this paper, we focus on a unified approach for reconstructing mammals …

title = {AniMer: Animal Pose and Shape Estimation Using Family Aware Transformer}, author = {Lyu, Jin and Zhu, Tianyi and Gu, Yi and Lin, Li and Cheng, Pujin and Liu, Yebin and Tang, Xiaoying and An, …

A key insight of AniMer is its integration of a high-capacity Transformer-based backbone and an animal family supervised contrastive learning scheme, unifying the discriminative understanding of various …

In this paper, we present AniMer, a systematic approach pursuing accurate animal pose and shape estimation using Transformer which surpasses existing methodologies on all benchmarks.

To address these limitations, we introduce AniMer+, an extended version of our scalable AniMer framework. In this paper, we focus on a unified approach for reconstructing mammals (mammalia) …

Dec 1, 2024 · A key insight of AniMer is its integration of a high-capacity Transformer-based backbone and an animal family supervised contrastive learning scheme, unifying the discriminative …

AniMer: Animal Pose and Shape Estimation Using Family Aware Transformer (CVPR2025) - luoxue-star/AniMer

To address these limitations, we introduce AniMer+, an extended version of our scalable AniMer framework. In this paper, we focus on a unified approach for reconstructing mammals (mammalia) …

A key insight of AniMer is its integration of a high-capacity Transformer-based backbone and an animal family supervised contrastive learning scheme, unifying the discriminative understanding of various …

We propose AniMer, an animal pose and shape estimation network benefiting from a high-capacity Transformer backbone and an integrated dataset covering most avail-able mammal datasets.