{"id":{"repo_id":"cambridge","oai_identifier":"oai:www.repository.cam.ac.uk:1810/267905"},"canonical_url":"https://search.dev.ndltd.org/etd/cambridge/oai:www.repository.cam.ac.uk:1810/267905","repository":{"repo_id":"cambridge","name":"Cambridge University","base_url":"https://api.repository.cam.ac.uk/server/oai/request"},"display":{"title":"Gaze Estimation with Graphics","abstract":"Gaze estimation systems determine where someone is looking. Gaze is used for a wide range of applications including market research, usability studies, and gaze-based interfaces. Traditional equipment uses special hardware. To bring gaze estimation mainstream, researchers are exploring approaches that use commodity hardware alone. My work addresses two outstanding problems in this field: 1) it is hard to collect good ground truth eye images for machine learning, and 2) gaze estimation systems do not generalize well -- once they are trained with images from one scenario, they do not work in another scenario. In this dissertation I address these problems in two different ways: learning-by-synthesis and analysis-by-synthesis. Learning-by-synthesis is the process of training a machine learning system with synthetic data, i.e. data that has been rendered with graphics rather than collected by hand. Analysis-by-synthesis is a computer vision strategy that couples a generative model of image formation (synthesis) with a perceptive model of scene comparison (analysis). The goal is to synthesize an image that best matches an observed image. In this dissertation I present three main contributions. First, I present a new method for training gaze estimation systems that use machine learning: learning-by-synthesis using 3D head scans and photorealistic rendering. Second, I present a new morphable model of the eye region. I show how this model can be used to generate large amounts of varied data for learning-by-synthesis. Third, I present a new method for gaze estimation: analysis-by-synthesis. I demonstrate how analysis-by-synthesis can generalize to different scenarios, estimating gaze in a device- and person- independent manner.","abstract_html":"Gaze estimation systems determine where someone is looking. Gaze is used for a wide range of applications including market research, usability studies, and gaze-based interfaces. Traditional equipment uses special hardware. To bring gaze estimation mainstream, researchers are exploring approaches that use commodity hardware alone. My work addresses two outstanding problems in this field: 1) it is hard to collect good ground truth eye images for machine learning, and 2) gaze estimation systems do not generalize well -- once they are trained with images from one scenario, they do not work in another scenario. In this dissertation I address these problems in two different ways: learning-by-synthesis and analysis-by-synthesis. Learning-by-synthesis is the process of training a machine learning system with synthetic data, i.e. data that has been rendered with graphics rather than collected by hand. Analysis-by-synthesis is a computer vision strategy that couples a generative model of image formation (synthesis) with a perceptive model of scene comparison (analysis). The goal is to synthesize an image that best matches an observed image. In this dissertation I present three main contributions. First, I present a new method for training gaze estimation systems that use machine learning: learning-by-synthesis using 3D head scans and photorealistic rendering. Second, I present a new morphable model of the eye region. I show how this model can be used to generate large amounts of varied data for learning-by-synthesis. Third, I present a new method for gaze estimation: analysis-by-synthesis. I demonstrate how analysis-by-synthesis can generalize to different scenarios, estimating gaze in a device- and person- independent manner.","abstract_has_math":false,"creators":["Wood, Erroll William"],"institution":"University of Cambridge","degree_name":"Doctor of Philosophy (PhD)","degree_level":"Doctoral","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Robinson, Peter"],"committee_chairs":[],"committee_members":[],"year":2017,"date_issued":"2017-10-17","date_published":"2017-10-17","updated_at":"2026-07-22T22:24:01Z","subjects":["Graphics","Computer Vision","Eye Tracking","Gaze Estimation"],"languages":["en"],"rights":[],"rights_urls":["https://apollo8-f-pro.lib.cam.ac.uk/bitstreams/2c64f455-4d38-4f6a-969b-68eddc288e1e/download","https://www.rioxx.net/licenses/all-rights-reserved/"],"identifier_entries":[]},"links":{"outbound_url":"https://doi.org/10.17863/CAM.13838","outbound_label":"DOI","outbound_source":"dc:identifier.doi"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Robinson, Peter"]},{"key":"dc:contributor.sponsor","label":"Sponsor","values":["EPSRC Doctoral Training Grant studentship for Erroll Wood (RG71269)"]},{"key":"dc:creator","label":"Author","values":["Wood, Erroll William"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.issued","label":"Date","values":["2017-10-17"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["University of Cambridge"]},{"key":"dc:relation.isreferencedby.uri","label":"Dc Relation Isreferencedby URI","values":["https://www.repository.cam.ac.uk/handle/1810/267905"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["Doctoral"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["Doctor of Philosophy (PhD)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Graphics","Computer Vision","Eye Tracking","Gaze Estimation"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["https://apollo8-f-pro.lib.cam.ac.uk/bitstreams/2c64f455-4d38-4f6a-969b-68eddc288e1e/download","https://www.rioxx.net/licenses/all-rights-reserved/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.doi","label":"DOI","values":["10.17863/CAM.13838"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://apollo8-f-pro.lib.cam.ac.uk/bitstreams/3f0e1b9e-963c-4e01-b1ee-b1e3195dc518/download"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Gaze estimation systems determine where someone is looking. Gaze is used for a wide range of applications including market research, usability studies, and gaze-based interfaces. Traditional equipment uses special hardware. To bring gaze estimation mainstream, researchers are exploring approaches that use commodity hardware alone. My work addresses two outstanding problems in this field: 1) it is hard to collect good ground truth eye images for machine learning, and 2) gaze estimation systems do not generalize well -- once they are trained with images from one scenario, they do not work in another scenario. In this dissertation I address these problems in two different ways: learning-by-synthesis and analysis-by-synthesis. Learning-by-synthesis is the process of training a machine learning system with synthetic data, i.e. data that has been rendered with graphics rather than collected by hand. Analysis-by-synthesis is a computer vision strategy that couples a generative model of image formation (synthesis) with a perceptive model of scene comparison (analysis). The goal is to synthesize an image that best matches an observed image. In this dissertation I present three main contributions. First, I present a new method for training gaze estimation systems that use machine learning: learning-by-synthesis using 3D head scans and photorealistic rendering. Second, I present a new morphable model of the eye region. I show how this model can be used to generate large amounts of varied data for learning-by-synthesis. Third, I present a new method for gaze estimation: analysis-by-synthesis. I demonstrate how analysis-by-synthesis can generalize to different scenarios, estimating gaze in a device- and person- independent manner."]},{"key":"dc:format.checksum.md5","label":"Dc Format Checksum Md5","values":["03398f6d2997af32ebe4155ec6403b30","87eda9de84448d1f82354d60eee3eb5f"]},{"key":"dc:title","label":"Title","values":["Gaze Estimation with Graphics"]}]}],"canonical_facts":{"dc:contributor.advisor":["Robinson, Peter"],"dc:contributor.sponsor":["EPSRC Doctoral Training Grant studentship for Erroll Wood (RG71269)"],"dc:creator":["Wood, Erroll William"],"dc:date.issued":["2017-10-17"],"dc:description.abstract":["Gaze estimation systems determine where someone is looking. Gaze is used for a wide range of applications including market research, usability studies, and gaze-based interfaces. Traditional equipment uses special hardware. To bring gaze estimation mainstream, researchers are exploring approaches that use commodity hardware alone. My work addresses two outstanding problems in this field: 1) it is hard to collect good ground truth eye images for machine learning, and 2) gaze estimation systems do not generalize well -- once they are trained with images from one scenario, they do not work in another scenario. In this dissertation I address these problems in two different ways: learning-by-synthesis and analysis-by-synthesis. Learning-by-synthesis is the process of training a machine learning system with synthetic data, i.e. data that has been rendered with graphics rather than collected by hand. Analysis-by-synthesis is a computer vision strategy that couples a generative model of image formation (synthesis) with a perceptive model of scene comparison (analysis). The goal is to synthesize an image that best matches an observed image. In this dissertation I present three main contributions. First, I present a new method for training gaze estimation systems that use machine learning: learning-by-synthesis using 3D head scans and photorealistic rendering. Second, I present a new morphable model of the eye region. I show how this model can be used to generate large amounts of varied data for learning-by-synthesis. Third, I present a new method for gaze estimation: analysis-by-synthesis. I demonstrate how analysis-by-synthesis can generalize to different scenarios, estimating gaze in a device- and person- independent manner."],"dc:format.checksum.md5":["03398f6d2997af32ebe4155ec6403b30","87eda9de84448d1f82354d60eee3eb5f"],"dc:identifier.doi":["10.17863/CAM.13838"],"dc:identifier.uri":["https://apollo8-f-pro.lib.cam.ac.uk/bitstreams/3f0e1b9e-963c-4e01-b1ee-b1e3195dc518/download"],"dc:language":["en"],"dc:publisher.institution":["University of Cambridge"],"dc:relation.isreferencedby.uri":["https://www.repository.cam.ac.uk/handle/1810/267905"],"dc:rights":["https://apollo8-f-pro.lib.cam.ac.uk/bitstreams/2c64f455-4d38-4f6a-969b-68eddc288e1e/download","https://www.rioxx.net/licenses/all-rights-reserved/"],"dc:subject":["Graphics","Computer Vision","Eye Tracking","Gaze Estimation"],"dc:title":["Gaze Estimation with Graphics"],"dc:type":["Thesis"],"dc:type.qualificationlevel":["Doctoral"],"dc:type.qualificationname":["Doctor of Philosophy (PhD)"]},"updated_at":"2026-07-22T22:24:01Z"}