Diffusion Models Enable Zero-Shot Pose Estimation for Lower-Limb Prosthetic Users (2312.07854v1)
Abstract: The application of 2D markerless gait analysis has garnered increasing interest and application within clinical settings. However, its effectiveness in the realm of lower-limb amputees has remained less than optimal. In response, this study introduces an innovative zero-shot method employing image generation diffusion models to achieve markerless pose estimation for lower-limb prosthetics, presenting a promising solution to gait analysis for this specific population. Our approach demonstrates an enhancement in detecting key points on prosthetic limbs over existing methods, and enables clinicians to gain invaluable insights into the kinematics of lower-limb amputees across the gait cycle. The outcomes obtained not only serve as a proof-of-concept for the feasibility of this zero-shot approach but also underscore its potential in advancing rehabilitation through gait analysis for this unique population.
- A. Esquenazi, Gait Analysis in Lower-Limb Amputation and Prosthetic Rehabilitation 25 (1) 153–167. doi:10.1016/j.pmr.2013.09.006. URL https://linkinghub.elsevier.com/retrieve/pii/S1047965113000739
- arXiv:420566.
- arXiv:1124978.
- doi:10.1016/j.medengphy.2020.11.005. URL https://linkinghub.elsevier.com/retrieve/pii/S1350453320301697
- doi:10.3390/fi13080194. URL https://www.mdpi.com/1999-5903/13/8/194
- doi:10.1159/000520732. URL https://www.karger.com/Article/FullText/520732
- doi:10.1145/3341105.3373963. URL https://dl.acm.org/doi/10.1145/3341105.3373963
- doi:10.1155/2019/2085039. URL https://www.hindawi.com/journals/bmri/2019/2085039/
- doi:10.1016/j.gaitpost.2010.03.007. URL https://linkinghub.elsevier.com/retrieve/pii/S0966636210000779
- doi:10.1016/j.humov.2018.04.003. URL https://linkinghub.elsevier.com/retrieve/pii/S0167945717305407
- doi:10.1016/j.cviu.2019.102897. URL https://linkinghub.elsevier.com/retrieve/pii/S1077314219301778
- arXiv:1605.03170. URL http://arxiv.org/abs/1605.03170
- doi:10.1016/j.neuron.2020.09.017. URL https://linkinghub.elsevier.com/retrieve/pii/S0896627320307170
- doi:10.1109/TPAMI.2019.2929257. URL https://ieeexplore.ieee.org/document/8765346/
- doi:10.1101/2022.07.07.499061. URL http://biorxiv.org/lookup/doi/10.1101/2022.07.07.499061
- doi:10.1016/j.gaitpost.2022.08.008. URL https://linkinghub.elsevier.com/retrieve/pii/S0966636222004738
- doi:10.1371/journal.pcbi.1008935. URL https://dx.plos.org/10.1371/journal.pcbi.1008935
- doi:10.1101/2022.11.10.22282089. URL http://medrxiv.org/lookup/doi/10.1101/2022.11.10.22282089
- doi:10.1038/s41593-018-0209-y. URL https://www.nature.com/articles/s41593-018-0209-y
- doi:10.48550/ARXIV.2302.05543.
- Mission gait. URL https://www.youtube.com/@MissionGait
- doi:10.1371/journal.pone.0165287. URL https://dx.plos.org/10.1371/journal.pone.0165287
- doi:10.3389/fspor.2020.00050. URL https://www.frontiersin.org/article/10.3389/fspor.2020.00050/full
- doi:10.1371/journal.pone.0223549. URL https://dx.plos.org/10.1371/journal.pone.0223549
- doi:10.1109/ICAMechS54019.2021.9661562. URL https://ieeexplore.ieee.org/document/9661562/
- doi:10.1109/ACCESS.2020.3006423. URL https://ieeexplore.ieee.org/document/9131774/
- doi:10.1016/j.humov.2019.03.008. URL https://linkinghub.elsevier.com/retrieve/pii/S0167945718307577
- doi:10.1016/j.gaitpost.2016.07.007. URL https://linkinghub.elsevier.com/retrieve/pii/S0966636216301448
- doi:10.1038/s41598-021-00212-x. URL https://www.nature.com/articles/s41598-021-00212-x
Sponsored by Paperpile, the PDF & BibTeX manager trusted by top AI labs.
Get 30 days freePaper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.