A Cycle Ride to HDR: Semantics Aware Self-Supervised Framework for Unpaired LDR-to-HDR Image Reconstruction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911230296326144 |
|---|---|
| author | Barua, Hrishav Bakul Stefanov, Kalin Che, Lemuel Lai En Dhall, Abhinav Wong, KokSheik Krishnasamy, Ganesh |
| author_facet | Barua, Hrishav Bakul Stefanov, Kalin Che, Lemuel Lai En Dhall, Abhinav Wong, KokSheik Krishnasamy, Ganesh |
| contents | Reconstruction of High Dynamic Range (HDR) from Low Dynamic Range (LDR) images is an important computer vision task. There is a significant amount of research utilizing both conventional non-learning methods and modern data-driven approaches, focusing on using both single-exposed and multi-exposed LDR for HDR image reconstruction. However, most current state-of-the-art methods require high-quality paired {LDR;HDR} datasets with limited literature use of unpaired datasets, that is, methods that learn the LDR-HDR mapping between domains. This paper proposes CycleHDR, a method that integrates self-supervision into a modified semantic- and cycle-consistent adversarial architecture that utilizes unpaired LDR and HDR datasets for training. Our method introduces novel artifact- and exposure-aware generators to address visual artifact removal. It also puts forward an encoder and loss to address semantic consistency, another under-explored topic. CycleHDR is the first to use semantic and contextual awareness for the LDR-HDR reconstruction task in a self-supervised setup. The method achieves state-of-the-art performance across several benchmark datasets and reconstructs high-quality HDR images. The official website of this work is available at: https://github.com/HrishavBakulBarua/Cycle-HDR |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_15068 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Cycle Ride to HDR: Semantics Aware Self-Supervised Framework for Unpaired LDR-to-HDR Image Reconstruction Barua, Hrishav Bakul Stefanov, Kalin Che, Lemuel Lai En Dhall, Abhinav Wong, KokSheik Krishnasamy, Ganesh Computer Vision and Pattern Recognition Artificial Intelligence Graphics Machine Learning Robotics Artificial intelligence, Computer vision, Machine learning, Deep learning I.3.3; I.4.5 Reconstruction of High Dynamic Range (HDR) from Low Dynamic Range (LDR) images is an important computer vision task. There is a significant amount of research utilizing both conventional non-learning methods and modern data-driven approaches, focusing on using both single-exposed and multi-exposed LDR for HDR image reconstruction. However, most current state-of-the-art methods require high-quality paired {LDR;HDR} datasets with limited literature use of unpaired datasets, that is, methods that learn the LDR-HDR mapping between domains. This paper proposes CycleHDR, a method that integrates self-supervision into a modified semantic- and cycle-consistent adversarial architecture that utilizes unpaired LDR and HDR datasets for training. Our method introduces novel artifact- and exposure-aware generators to address visual artifact removal. It also puts forward an encoder and loss to address semantic consistency, another under-explored topic. CycleHDR is the first to use semantic and contextual awareness for the LDR-HDR reconstruction task in a self-supervised setup. The method achieves state-of-the-art performance across several benchmark datasets and reconstructs high-quality HDR images. The official website of this work is available at: https://github.com/HrishavBakulBarua/Cycle-HDR |
| title | A Cycle Ride to HDR: Semantics Aware Self-Supervised Framework for Unpaired LDR-to-HDR Image Reconstruction |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Graphics Machine Learning Robotics Artificial intelligence, Computer vision, Machine learning, Deep learning I.3.3; I.4.5 |
| url | https://arxiv.org/abs/2410.15068 |