{"id":{"repo_id":"umkc","oai_identifier":"oai:mospace.umsystem.edu:10355/65996"},"canonical_url":"https://search.dev.ndltd.org/etd/umkc/oai:mospace.umsystem.edu:10355/65996","repository":{"repo_id":"umkc","name":"University of Missouri - Kansas City","base_url":"https://mospace.umsystem.edu/oai/request"},"display":{"title":"3D Hand Pose Estimation Via a Lightweight Deep Learning Model","abstract":"Deep Learning with depth cameras has enabled 3D hand pose estimation from RGBD images. Commercial solutions like Leap Motion and Intel RealSense™ use stereoscopic sensors or IR illumination-based methods to capture the depth in a photograph and further estimate pose using Deep Learning (DL) methods. These hand pose estimation work has not considered the use of virtual reality (VR) apps on mobile devices because this requires extensive computational resources including hardware for processing the acquired depth. Previous works in 3D hand pose estimation are based on the large pre-trained DL models in the pose estimation pipeline which are not suitable to run on mobile devices. In this work, we address the problem of hand pose estimation from monocular RGB images (instead of RGBD images) and making DL models suitable to run on mobile VR. This task is so challenging due to the missing depth information, we propose a deep neural network (DNN) that learns a 3D hand articulated prior to estimating the 3D pose from RGB images. Our approach comprises of (1) Localization network predicts the location of hands in the image, (2) sparse adversarial auto-encoders trained on hand RGB images, and (3) adversarial auto-encoder for capturing 3D hand pose distributions. Finally, the proposed model yielded the accuracy comparable to state-of-the-art 3D hand pose estimation. However, our model is much smaller than the existing models so that we significantly accelerated the model execution and greatly reduced the run-time 2.6X faster than the current solutions.","abstract_html":"Deep Learning with depth cameras has enabled 3D hand pose estimation from RGBD images. Commercial solutions like Leap Motion and Intel RealSense™ use stereoscopic sensors or IR illumination-based methods to capture the depth in a photograph and further estimate pose using Deep Learning (DL) methods. These hand pose estimation work has not considered the use of virtual reality (VR) apps on mobile devices because this requires extensive computational resources including hardware for processing the acquired depth. Previous works in 3D hand pose estimation are based on the large pre-trained DL models in the pose estimation pipeline which are not suitable to run on mobile devices. In this work, we address the problem of hand pose estimation from monocular RGB images (instead of RGBD images) and making DL models suitable to run on mobile VR. This task is so challenging due to the missing depth information, we propose a deep neural network (DNN) that learns a 3D hand articulated prior to estimating the 3D pose from RGB images. Our approach comprises of (1) Localization network predicts the location of hands in the image, (2) sparse adversarial auto-encoders trained on hand RGB images, and (3) adversarial auto-encoder for capturing 3D hand pose distributions. Finally, the proposed model yielded the accuracy comparable to state-of-the-art 3D hand pose estimation. However, our model is much smaller than the existing models so that we significantly accelerated the model execution and greatly reduced the run-time 2.6X faster than the current solutions.","abstract_has_math":false,"creators":["Suggala, Prudhvi Sai"],"institution":"University of Missouri -- Kansas City","degree_name":"M.S. (Master of Science)","degree_level":"Masters","degree_discipline":"Computer Science (UMKC)","degree_department":null,"school":null,"contributors":[],"advisors":["Lee, Yugyung, 1960-"],"committee_chairs":[],"committee_members":[],"year":2018,"date_issued":"2018","date_published":"2018","updated_at":"2026-07-24T05:18:49Z","subjects":[],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10355/65996","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Lee, Yugyung, 1960-"]},{"key":"dc:creator","label":"Author","values":["Suggala, Prudhvi Sai"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2018-09-27T14:23:58Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2018-09-27T14:23:58Z"]},{"key":"dc:date.issued","label":"Date","values":["2018"]},{"key":"dc:publisher","label":"Institution","values":["University of Missouri -- Kansas City"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science (UMKC)"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S. (Master of Science)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Missouri--Kansas City"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10355/65996"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Title from PDF of title page, viewed September 28, 2018","Thesis advisor: Yugyung Lee","Vita","Includes bibliographical references (pages 32-33)","Thesis (M.S.)--School of Computing and Engineering. University of Missouri--Kansas City, 2018"]},{"key":"dc:description.abstract","label":"Abstract","values":["Deep Learning with depth cameras has enabled 3D hand pose estimation from RGBD images. Commercial solutions like Leap Motion and Intel RealSense™ use stereoscopic sensors or IR illumination-based methods to capture the depth in a photograph and further estimate pose using Deep Learning (DL) methods. These hand pose estimation work has not considered the use of virtual reality (VR) apps on mobile devices because this requires extensive computational resources including hardware for processing the acquired depth. Previous works in 3D hand pose estimation are based on the large pre-trained DL models in the pose estimation pipeline which are not suitable to run on mobile devices. In this work, we address the problem of hand pose estimation from monocular RGB images (instead of RGBD images) and making DL models suitable to run on mobile VR. This task is so challenging due to the missing depth information, we propose a deep neural network (DNN) that learns a 3D hand articulated prior to estimating the 3D pose from RGB images. Our approach comprises of (1) Localization network predicts the location of hands in the image, (2) sparse adversarial auto-encoders trained on hand RGB images, and (3) adversarial auto-encoder for capturing 3D hand pose distributions. Finally, the proposed model yielded the accuracy comparable to state-of-the-art 3D hand pose estimation. However, our model is much smaller than the existing models so that we significantly accelerated the model execution and greatly reduced the run-time 2.6X faster than the current solutions."]},{"key":"dc:title","label":"Title","values":["3D Hand Pose Estimation Via a Lightweight Deep Learning Model"]}]}],"canonical_facts":{"dc:contributor.advisor":["Lee, Yugyung, 1960-"],"dc:creator":["Suggala, Prudhvi Sai"],"dc:date.accessioned":["2018-09-27T14:23:58Z"],"dc:date.available":["2018-09-27T14:23:58Z"],"dc:date.issued":["2018"],"dc:description":["Title from PDF of title page, viewed September 28, 2018","Thesis advisor: Yugyung Lee","Vita","Includes bibliographical references (pages 32-33)","Thesis (M.S.)--School of Computing and Engineering. University of Missouri--Kansas City, 2018"],"dc:description.abstract":["Deep Learning with depth cameras has enabled 3D hand pose estimation from RGBD images. Commercial solutions like Leap Motion and Intel RealSense™ use stereoscopic sensors or IR illumination-based methods to capture the depth in a photograph and further estimate pose using Deep Learning (DL) methods. These hand pose estimation work has not considered the use of virtual reality (VR) apps on mobile devices because this requires extensive computational resources including hardware for processing the acquired depth. Previous works in 3D hand pose estimation are based on the large pre-trained DL models in the pose estimation pipeline which are not suitable to run on mobile devices. In this work, we address the problem of hand pose estimation from monocular RGB images (instead of RGBD images) and making DL models suitable to run on mobile VR. This task is so challenging due to the missing depth information, we propose a deep neural network (DNN) that learns a 3D hand articulated prior to estimating the 3D pose from RGB images. Our approach comprises of (1) Localization network predicts the location of hands in the image, (2) sparse adversarial auto-encoders trained on hand RGB images, and (3) adversarial auto-encoder for capturing 3D hand pose distributions. Finally, the proposed model yielded the accuracy comparable to state-of-the-art 3D hand pose estimation. However, our model is much smaller than the existing models so that we significantly accelerated the model execution and greatly reduced the run-time 2.6X faster than the current solutions."],"dc:identifier.uri":["https://hdl.handle.net/10355/65996"],"dc:publisher":["University of Missouri -- Kansas City"],"dc:title":["3D Hand Pose Estimation Via a Lightweight Deep Learning Model"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer Science (UMKC)"],"thesis:degree_level":["Masters"],"thesis:degree_name":["M.S. (Master of Science)"],"thesis:institution_name":["University of Missouri--Kansas City"]},"updated_at":"2026-07-24T05:18:49Z"}