AJAHR:
Amputated Joint Aware
3D Human Mesh Recovery

ICCV 2025

1 Dept. of Advanced Imaging, GSAIM, Chung-Ang University, Seoul, Korea
2 Dept. of Artificial Intelligence, Chung-Ang University, Seoul, Korea
3 Korea Institute of Industrial Technology (KITECH), Seoul, Korea

* Equal contribution
Corresponding author
Teaser Image

Examples of Human Mesh Recovery for Amputee and Non-Amputee Individuals. Column (a) shows input images: the top row includes a non-amputee (left) and an amputee (right), while the bottom row shows an amputee. Our method AJAHR (b) accurately handles both cases, whereas (c), (d), and (e) often misinterpret amputated limbs as intact and infer implausible poses in missing regions.

Abstract

Existing human mesh recovery methods assume a standard human body structure, overlooking diverse anatomical conditions such as limb loss. This assumption introduces bias when applied to individuals with amputations—a limitation further exacerbated by the scarcity of suitable datasets. To address this gap, we propose Amputated Joint Aware 3D Human Mesh Recovery (AJAHR), which is an adaptive pose estimation framework that improves mesh reconstruction for individuals with limb loss. Our model integrates a body-part amputation classifier, jointly trained with the mesh recovery network, to detect potential amputations. We also introduce Amputee 3D (A3D), which is a synthetic dataset offering a wide range of amputee poses for robust training. While maintaining competitive performance on non-amputees, our approach achieves state-ofthe-art results for amputated individuals.

Video Presentation

Another Carousel

Poster

BibTeX

BibTex Code Here