ResiHMR：面向截肢个体的残肢感知单图像三维人体网格恢复
ResiHMR: Residual-Limb Aware Single-Image 3D Human Mesh Recovery for Individuals with Limb Loss
针对非标准肢体解剖结构，提出拓扑自适应优化和显式残肢终止几何重建，可推广到其他固定拓扑模型难以表示的人体形态（如截肢、先天畸形）的单图像三维重建任务。
原文依据 ResiHMR adopts residual-limb keypoints and introduces two components: (i) a topology-adaptive Residual Anchor-Factor Optimization module
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论单图像人体网格恢复提供了一种紧凑的、以人为中心的三维表示，可支持分析、动画、增强现实与虚拟现实、康复以及人机交互。然而，现有系统施加了完整肢体先验，在截肢个体上性能下降，因为固定拓扑模型无法表示残肢。在本工作中，我们提出ResiHMR，一个残肢感知的单图像三维人体建模框架。ResiHMR采用残肢关键点，并引入两个组件：(i) 拓扑自适应的残肢锚点-因子优化模块，将估计约束在解剖有效结构的观测运动学子图上；(ii) 基于几何的残肢重建模块，估计残肢边界和凸性肢体终止几何。这些模块共同将拓扑感知优化和显式终止几何作为非标准肢体解剖下人体网格恢复的工具。与固定拓扑中的关节移除方法不同，ResiHMR显式重建残肢表面并使优化与肢体缺失拓扑对齐，从而更好地匹配假肢生物力学和实际使用。据我们所知，这是首个显式重建残肢表面并对截肢个体执行拓扑自适应优化的单图像HMR系统。在精心整理的截肢真实图像数据集上，ResiHMR在SMPLify-X和HSMR骨干下均提升了重建质量，SMPLify-X下完整关节二维MPJPE从41.32降至37.40，HSMR下残肢二维MPJPE从73.61降至23.19。
英文原文摘要 1655 字符
Single-image human mesh recovery provides a compact 3D, person-centric representation that supports analysis, animation, AR and VR, rehabilitation, and human-computer interaction. However, prevailing systems impose an intact-limb prior and degrade on people with limb loss, because fixed-topology models cannot represent residual limbs. In this work, we present ResiHMR, a residual-limb aware framework for single-image 3D human modeling. ResiHMR adopts residual-limb keypoints and introduces two components: (i) a topology-adaptive Residual Anchor-Factor Optimization module that constrains estimation to the observed kinematic subgraph of anatomically valid structures, and (ii) a geometry-based Residual-Limb Reconstruction module that estimates residual-limb boundaries and convex limb-termination geometry. Together, these modules introduce topology-aware optimization and explicit termination geometry as tools for human mesh recovery under non-standard limb anatomy. Unlike joint-removal methods in a fixed topology, ResiHMR explicitly reconstructs residual-limb surfaces and aligns optimization with limb-loss topology, which better matches prosthetic biomechanics and real-world use. To the best of our knowledge, this is the first single-image HMR system that explicitly reconstructs residual-limb surfaces and performs topology-adaptive optimization for individuals with limb loss. On a curated dataset of real-world images with limb loss, ResiHMR improves reconstruction quality under both SMPLify-X and HSMR backbones, reducing intact-joint 2D MPJPE from 41.32 to 37.40 with SMPLify-X and residual-limb 2D MPJPE from 73.61 to 23.19 with HSMR.