{"id":{"repo_id":"uoit","oai_identifier":"oai:ontariotechu.scholaris.ca:10155/1993"},"canonical_url":"https://search.dev.ndltd.org/etd/uoit/oai:ontariotechu.scholaris.ca:10155/1993","repository":{"repo_id":"uoit","name":"Ontario Institute of Technology","base_url":"https://ontariotechu.scholaris.ca/server/oai/request"},"display":{"title":"Hyperspectral image compression using implicit neural representations","abstract":"Hyperspectral images (HSI) capture the full electromagnetic spectrum for each pixel in a scene. They often hold hundreds of channels per pixel, providing significantly more information compared to a comparably sized RGB color image. As the cost of obtaining these images decreases, there is a need to create effective ways for storing, transferring, and interpreting hyperspectral data. In this thesis, we develop several neural compression-based methods for hyperspectral images. Our methodology relies on transforming hyperspectral images into implicit neural representations (INR), specifically neural functions that establish a correspondence between coordinates and features. We use a multilayer perception (MLP) network with sinusoidal activation functions that “learns” to map pixel locations to pixel spectrum for a given hyperspectral image. This representation thus acts as a compressed encoding of this image, and the original image is reconstructed by evaluating this network at each pixel location. In the other variation of using implicit neural representation to compress hyperspectral images, a sampling scheme is introduced to achieve better compression times while keeping decoding errors low. In our other method, instead of explicitly saving the weights of the implicit neural representation, the modulations that are applied to a base network that has been meta-learned are recorded. These modulations serve as a compressed coding for the hyperspectral image. An assessment of the proposed approach was conducted using four benchmarks: Indian Pines, Jasper Ridge, Pavia University, and Cuprite. The proposed method is evaluated against sixteen other schemes ((1) JPEG, (2) JPEG2000, (3) PCA-DCT, (4) PCA-JPEG2000, (5) MPEG, (6) X264, (7) X265, (8) PCA-X264, (9) PCA-X265, (10) FPCA-JPEG2000, (11) 3D-DCT, (12) 3D-DWT-SVR, (13) WSRC, (14) HEVC, (15) RPM, and (16) 3D-SPECK.) for hyperspectral image compression, and according to the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) metrics, the method developed in this study achieves state-of-the-art compression rates at low-bit rates. We also used a large hyperspectral image dataset, compressed it using our methods, and compared our results with JPEG and MPEG. Finally, we conducted task-aware hyperspectral image compression, in which regions are chosen according to a task, and hyperspectral images are compressed using our proposed method.","abstract_html":"Hyperspectral images (HSI) capture the full electromagnetic spectrum for each pixel in a scene. They often hold hundreds of channels per pixel, providing significantly more information compared to a comparably sized RGB color image. As the cost of obtaining these images decreases, there is a need to create effective ways for storing, transferring, and interpreting hyperspectral data. In this thesis, we develop several neural compression-based methods for hyperspectral images. Our methodology relies on transforming hyperspectral images into implicit neural representations (INR), specifically neural functions that establish a correspondence between coordinates and features. We use a multilayer perception (MLP) network with sinusoidal activation functions that “learns” to map pixel locations to pixel spectrum for a given hyperspectral image. This representation thus acts as a compressed encoding of this image, and the original image is reconstructed by evaluating this network at each pixel location. In the other variation of using implicit neural representation to compress hyperspectral images, a sampling scheme is introduced to achieve better compression times while keeping decoding errors low. In our other method, instead of explicitly saving the weights of the implicit neural representation, the modulations that are applied to a base network that has been meta-learned are recorded. These modulations serve as a compressed coding for the hyperspectral image. An assessment of the proposed approach was conducted using four benchmarks: Indian Pines, Jasper Ridge, Pavia University, and Cuprite. The proposed method is evaluated against sixteen other schemes ((1) JPEG, (2) JPEG2000, (3) PCA-DCT, (4) PCA-JPEG2000, (5) MPEG, (6) X264, (7) X265, (8) PCA-X264, (9) PCA-X265, (10) FPCA-JPEG2000, (11) 3D-DCT, (12) 3D-DWT-SVR, (13) WSRC, (14) HEVC, (15) RPM, and (16) 3D-SPECK.) for hyperspectral image compression, and according to the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) metrics, the method developed in this study achieves state-of-the-art compression rates at low-bit rates. We also used a large hyperspectral image dataset, compressed it using our methods, and compared our results with JPEG and MPEG. Finally, we conducted task-aware hyperspectral image compression, in which regions are chosen according to a task, and hyperspectral images are compressed using our proposed method.","abstract_has_math":false,"creators":["Rezasoltani, Shima"],"institution":"University of Ontario Institute of Technology","degree_name":"Doctor of Philosophy (PhD)","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Qureshi, Faisal"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-07-01","date_published":"2025-07-01","updated_at":"2026-07-24T05:35:38Z","subjects":[],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10155/1993","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Qureshi, Faisal"]},{"key":"dc:creator","label":"Author","values":["Rezasoltani, Shima"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-09-18T18:03:06Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-09-18T18:03:06Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-07-01"]},{"key":"dc:type","label":"Dc Type","values":["Dissertation"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy (PhD)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Ontario Institute of Technology"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10155/1993"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Hyperspectral images (HSI) capture the full electromagnetic spectrum for each pixel in a scene. They often hold hundreds of channels per pixel, providing significantly more information compared to a comparably sized RGB color image. As the cost of obtaining these images decreases, there is a need to create effective ways for storing, transferring, and interpreting hyperspectral data. In this thesis, we develop several neural compression-based methods for hyperspectral images. Our methodology relies on transforming hyperspectral images into implicit neural representations (INR), specifically neural functions that establish a correspondence between coordinates and features. We use a multilayer perception (MLP) network with sinusoidal activation functions that “learns” to map pixel locations to pixel spectrum for a given hyperspectral image. This representation thus acts as a compressed encoding of this image, and the original image is reconstructed by evaluating this network at each pixel location. In the other variation of using implicit neural representation to compress hyperspectral images, a sampling scheme is introduced to achieve better compression times while keeping decoding errors low. In our other method, instead of explicitly saving the weights of the implicit neural representation, the modulations that are applied to a base network that has been meta-learned are recorded. These modulations serve as a compressed coding for the hyperspectral image. An assessment of the proposed approach was conducted using four benchmarks: Indian Pines, Jasper Ridge, Pavia University, and Cuprite. The proposed method is evaluated against sixteen other schemes ((1) JPEG, (2) JPEG2000, (3) PCA-DCT, (4) PCA-JPEG2000, (5) MPEG, (6) X264, (7) X265, (8) PCA-X264, (9) PCA-X265, (10) FPCA-JPEG2000, (11) 3D-DCT, (12) 3D-DWT-SVR, (13) WSRC, (14) HEVC, (15) RPM, and (16) 3D-SPECK.) for hyperspectral image compression, and according to the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) metrics, the method developed in this study achieves state-of-the-art compression rates at low-bit rates. We also used a large hyperspectral image dataset, compressed it using our methods, and compared our results with JPEG and MPEG. Finally, we conducted task-aware hyperspectral image compression, in which regions are chosen according to a task, and hyperspectral images are compressed using our proposed method."]},{"key":"dc:title","label":"Title","values":["Hyperspectral image compression using implicit neural representations"]}]}],"canonical_facts":{"dc:contributor.advisor":["Qureshi, Faisal"],"dc:creator":["Rezasoltani, Shima"],"dc:date.accessioned":["2025-09-18T18:03:06Z"],"dc:date.available":["2025-09-18T18:03:06Z"],"dc:date.issued":["2025-07-01"],"dc:description.abstract":["Hyperspectral images (HSI) capture the full electromagnetic spectrum for each pixel in a scene. They often hold hundreds of channels per pixel, providing significantly more information compared to a comparably sized RGB color image. As the cost of obtaining these images decreases, there is a need to create effective ways for storing, transferring, and interpreting hyperspectral data. In this thesis, we develop several neural compression-based methods for hyperspectral images. Our methodology relies on transforming hyperspectral images into implicit neural representations (INR), specifically neural functions that establish a correspondence between coordinates and features. We use a multilayer perception (MLP) network with sinusoidal activation functions that “learns” to map pixel locations to pixel spectrum for a given hyperspectral image. This representation thus acts as a compressed encoding of this image, and the original image is reconstructed by evaluating this network at each pixel location. In the other variation of using implicit neural representation to compress hyperspectral images, a sampling scheme is introduced to achieve better compression times while keeping decoding errors low. In our other method, instead of explicitly saving the weights of the implicit neural representation, the modulations that are applied to a base network that has been meta-learned are recorded. These modulations serve as a compressed coding for the hyperspectral image. An assessment of the proposed approach was conducted using four benchmarks: Indian Pines, Jasper Ridge, Pavia University, and Cuprite. The proposed method is evaluated against sixteen other schemes ((1) JPEG, (2) JPEG2000, (3) PCA-DCT, (4) PCA-JPEG2000, (5) MPEG, (6) X264, (7) X265, (8) PCA-X264, (9) PCA-X265, (10) FPCA-JPEG2000, (11) 3D-DCT, (12) 3D-DWT-SVR, (13) WSRC, (14) HEVC, (15) RPM, and (16) 3D-SPECK.) for hyperspectral image compression, and according to the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) metrics, the method developed in this study achieves state-of-the-art compression rates at low-bit rates. We also used a large hyperspectral image dataset, compressed it using our methods, and compared our results with JPEG and MPEG. Finally, we conducted task-aware hyperspectral image compression, in which regions are chosen according to a task, and hyperspectral images are compressed using our proposed method."],"dc:identifier.uri":["https://hdl.handle.net/10155/1993"],"dc:language.iso":["en"],"dc:title":["Hyperspectral image compression using implicit neural representations"],"dc:type":["Dissertation"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["Doctor of Philosophy (PhD)"],"thesis:institution_name":["University of Ontario Institute of Technology"]},"updated_at":"2026-07-24T05:35:38Z"}