{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/84859"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/84859","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Smoothness- transferred random field","abstract":"We propose a new random field (RF) model, smoothness-transfer random field (ST-RF) model, for image modeling. In the objective function of RF models, smoothness energy is defined with compatibility function to capture the relationship between neighboring local regions, while data energy for the evidence from local regions. Usually, the smoothness energy is constructed in terms of a fixed set of filters or basis which can be learned from training examples and steered to local structures in test examples. ST-RF, on the other hand, takes the data-driven approach to nonparametrically model the compatibility function for smoothness energy. The pipeline for our ST-RF model is as follows: first for each training example, we build a RF model with \"ground truth smoothness energy\", where the compatibility function is constructed from ground truth value. Then, for each test example, we use data-driven method to find its correspondence with training examples. Lastly, we construct the smoothness energy of ST-RF for each test example by transferring the compatibility function from matched region. After construction, we applies traditional RF inference and learning algorithms to obtain the final estimation. We demonstrate that with transferred ground truth smoothness, random field can achieve state-of-the-art results in stereo matching and image denoising on standard benchmark dataset.","abstract_html":"We propose a new random field (RF) model, smoothness-transfer random field (ST-RF) model, for image modeling. In the objective function of RF models, smoothness energy is defined with compatibility function to capture the relationship between neighboring local regions, while data energy for the evidence from local regions. Usually, the smoothness energy is constructed in terms of a fixed set of filters or basis which can be learned from training examples and steered to local structures in test examples. ST-RF, on the other hand, takes the data-driven approach to nonparametrically model the compatibility function for smoothness energy. The pipeline for our ST-RF model is as follows: first for each training example, we build a RF model with "ground truth smoothness energy", where the compatibility function is constructed from ground truth value. Then, for each test example, we use data-driven method to find its correspondence with training examples. Lastly, we construct the smoothness energy of ST-RF for each test example by transferring the compatibility function from matched region. After construction, we applies traditional RF inference and learning algorithms to obtain the final estimation. We demonstrate that with transferred ground truth smoothness, random field can achieve state-of-the-art results in stereo matching and image denoising on standard benchmark dataset.","abstract_has_math":false,"creators":["Wei, Donglai"],"institution":"Massachusetts Institute of Technology","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.","school":null,"contributors":[],"advisors":["William T. Freeman."],"committee_chairs":[],"committee_members":[],"year":2013,"date_issued":"2013","date_published":"2013","updated_at":"2026-07-22T22:22:10Z","subjects":["Electrical Engineering and Computer Science."],"languages":["eng"],"rights":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."],"rights_urls":["http://dspace.mit.edu/handle/1721.1/7582"],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1721.1/84859","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["William T. Freeman."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."]},{"key":"dc:creator","label":"Author","values":["Wei, Donglai"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2014-02-10T16:55:26Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2014-02-10T16:55:26Z"]},{"key":"dc:date.issued","label":"Date","values":["2013"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electrical Engineering and Computer Science."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://dspace.mit.edu/handle/1721.1/7582"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/1721.1/84859"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2013.","Title as it appears in Degrees awarded booklet, September 2013: Data driven stereo vision. Cataloged from PDF version of thesis.","Includes bibliographical references (pages 45-48)."]},{"key":"dc:description.abstract","label":"Abstract","values":["We propose a new random field (RF) model, smoothness-transfer random field (ST-RF) model, for image modeling. In the objective function of RF models, smoothness energy is defined with compatibility function to capture the relationship between neighboring local regions, while data energy for the evidence from local regions. Usually, the smoothness energy is constructed in terms of a fixed set of filters or basis which can be learned from training examples and steered to local structures in test examples. ST-RF, on the other hand, takes the data-driven approach to nonparametrically model the compatibility function for smoothness energy. The pipeline for our ST-RF model is as follows: first for each training example, we build a RF model with \"ground truth smoothness energy\", where the compatibility function is constructed from ground truth value. Then, for each test example, we use data-driven method to find its correspondence with training examples. Lastly, we construct the smoothness energy of ST-RF for each test example by transferring the compatibility function from matched region. After construction, we applies traditional RF inference and learning algorithms to obtain the final estimation. We demonstrate that with transferred ground truth smoothness, random field can achieve state-of-the-art results in stereo matching and image denoising on standard benchmark dataset."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.M."]},{"key":"dc:title","label":"Title","values":["Smoothness- transferred random field"]}]}],"canonical_facts":{"dc:contributor.advisor":["William T. Freeman."],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."],"dc:contributor.other":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."],"dc:creator":["Wei, Donglai"],"dc:date.accessioned":["2014-02-10T16:55:26Z"],"dc:date.available":["2014-02-10T16:55:26Z"],"dc:date.issued":["2013"],"dc:description":["Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2013.","Title as it appears in Degrees awarded booklet, September 2013: Data driven stereo vision. Cataloged from PDF version of thesis.","Includes bibliographical references (pages 45-48)."],"dc:description.abstract":["We propose a new random field (RF) model, smoothness-transfer random field (ST-RF) model, for image modeling. In the objective function of RF models, smoothness energy is defined with compatibility function to capture the relationship between neighboring local regions, while data energy for the evidence from local regions. Usually, the smoothness energy is constructed in terms of a fixed set of filters or basis which can be learned from training examples and steered to local structures in test examples. ST-RF, on the other hand, takes the data-driven approach to nonparametrically model the compatibility function for smoothness energy. The pipeline for our ST-RF model is as follows: first for each training example, we build a RF model with \"ground truth smoothness energy\", where the compatibility function is constructed from ground truth value. Then, for each test example, we use data-driven method to find its correspondence with training examples. Lastly, we construct the smoothness energy of ST-RF for each test example by transferring the compatibility function from matched region. After construction, we applies traditional RF inference and learning algorithms to obtain the final estimation. We demonstrate that with transferred ground truth smoothness, random field can achieve state-of-the-art results in stereo matching and image denoising on standard benchmark dataset."],"dc:description.degree":["S.M."],"dc:identifier.uri":["http://hdl.handle.net/1721.1/84859"],"dc:language.iso":["eng"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."],"dc:rights.uri":["http://dspace.mit.edu/handle/1721.1/7582"],"dc:subject":["Electrical Engineering and Computer Science."],"dc:title":["Smoothness- transferred random field"],"dc:type":["Thesis"]},"updated_at":"2026-07-22T22:22:10Z"}