{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T06:17:44Z","timestamp":1785392264095,"version":"3.55.0"},"reference-count":61,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T00:00:00Z","timestamp":1748563200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:p>Reliable visual perception is essential for autonomous driving test scenario generation, yet adverse weather and lighting variations pose significant challenges to simulation robustness and generalization. Traditional unpaired image-to-image translation methods primarily rely on RGB-based transformations, often resulting in geometric distortions and loss of structural consistency, which can negatively impact the realism and accuracy of generated test scenarios. To address these limitations, we propose a Depth-Aware Dual-Branch Generative Adversarial Network (DAB-GAN) that explicitly incorporates depth information to preserve spatial structures during scenario generation. The dual-branch generator processes both RGB and depth inputs, ensuring geometric fidelity, while a self-attention mechanism enhances spatial dependencies and local detail refinement. This enables the creation of realistic and structure-preserving test environments that are crucial for evaluating autonomous driving perception systems, especially under adverse weather conditions. Experimental results demonstrate that DAB-GAN outperforms existing unpaired image-to-image translation methods, achieving superior visual fidelity and maintaining depth-aware structural integrity. This approach provides a robust framework for generating diverse and challenging test scenarios, enhancing the development and validation of autonomous driving systems under various real-world conditions.<\/jats:p>","DOI":"10.3389\/fnbot.2025.1603964","type":"journal-article","created":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T06:11:41Z","timestamp":1748585501000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Depth-aware unpaired image-to-image translation for autonomous driving test scenario generation using a dual-branch GAN"],"prefix":"10.3389","volume":"19","author":[{"given":"Donghao","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenxin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cunbin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhou","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chonghao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minjie","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,5,30]]},"reference":[{"key":"ref1","author":"Agarwal","year":"2025"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"102631","DOI":"10.1016\/j.ecoinf.2024.102631","article-title":"Mula-Gan: multi-level attention Gan for enhanced underwater visibility","volume":"81","author":"Bakht","year":"2024","journal-title":"Ecol. Inform."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"2040","DOI":"10.1109\/TSE.2024.3420816","article-title":"Boundary state generation for testing and improvement of autonomous driving systems","volume":"50","author":"Biagiola","year":"2024","journal-title":"IEEE Trans. Softw. Eng."},{"key":"ref4","author":"Cai","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"3371","DOI":"10.1109\/IV55156.2024.10588675","article-title":"A review on scenario generation for testing autonomous vehicles","author":"Cai","year":"2024","journal-title":"IEEE Intell. Veh. Symp."},{"key":"ref6","author":"Cai","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"127730","DOI":"10.1016\/j.neucom.2024.127730","article-title":"Element-conditioned Gan for graphic layout generation","volume":"591","author":"Chen","year":"2024","journal-title":"Neurocomputing"},{"key":"ref8","author":"Chen","year":"2024"},{"key":"ref9","author":"Devlin","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"14994","DOI":"10.1038\/s41598-024-65540-0","article-title":"Agrigan: unpaired image dehazing via a cycle-consistent generative adversarial network for the agricultural plant phenotype","volume":"14","author":"Ding","year":"2024","journal-title":"Sci. Rep."},{"key":"ref11","author":"El Madawi","year":"2019"},{"key":"ref12","author":"Fernando","year":"2024"},{"key":"ref13","author":"Geiger","year":"2012"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"2672","DOI":"10.48550\/arXiv.1406.2661","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"2997","DOI":"10.1109\/TPAMI.2023.3339964","article-title":"Dagan plus plus: depth-aware generative adversarial network for talking head video generation","volume":"46","author":"Hong","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref16","author":"Hong","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1109\/TITS.2024.3490616","article-title":"A bayesian optimization method for finding the worst-case scenarios of autonomous vehicles","volume":"26","author":"Huang","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref18","author":"Ioannou","year":"2022"},{"key":"ref19","author":"Isola","year":"2017"},{"key":"ref20","author":"Karras","year":"2017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2106.12423","article-title":"Alias-free generative adversarial networks","volume":"34","author":"Karras","year":"","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"4217","DOI":"10.1109\/TPAMI.2020.2970919","article-title":"A style-based generator architecture for generative adversarial networks","volume":"43","author":"Karras","year":"","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref23","author":"Karras","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2306.01567","article-title":"Segment anything in high quality","volume":"36","author":"Ke","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"165963","DOI":"10.1109\/access.2024.3491792","article-title":"Light the way: an enhanced generative adversarial network framework for night-to-day image translation with improved quality","volume":"12","author":"Lakmal","year":"2024","journal-title":"IEEE Access"},{"key":"ref26","author":"Lambertenghi","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIV.2024.3504566","article-title":"Sustechgan: image generation for object detection in adverse conditions of autonomous driving","author":"Lan","year":"2024","journal-title":"IEEE Trans. Intell. Veh."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"5287","DOI":"10.3390\/s22145287","article-title":"Gan-based lidar translation between sunny and adverse weather for autonomous driving and driving simulation","volume":"22","author":"Lee","year":"2022","journal-title":"SENSORS-BASEL"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"14859","DOI":"10.1109\/TITS.2021.3134661","article-title":"Scegene: bio-inspired traffic scenario generation for autonomous driving testing","volume":"23","author":"Li","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref30","author":"Li","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"3211","DOI":"10.1109\/TIV.2023.3269428","article-title":"Advanced scenario generation for calibration and verification of autonomous vehicles","volume":"8","author":"Li","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"111431","DOI":"10.1016\/j.patcog.2025.111431","article-title":"Wtngan: unpaired image translation from white light images to narrow-band images","volume":"162","author":"Lin","year":"2025","journal-title":"Pattern Recogn."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1703.00848","article-title":"Unsupervised image-to-image translation networks","volume":"30","author":"Liu","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref34","author":"Liu","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1109\/TCI.2024.3402372","article-title":"Channel-spatial attention guided cyclegan for cbct-based synthetic ct generation to enable adaptive radiotherapy","volume":"10","author":"Liu","year":"2024","journal-title":"IEEE Trans. Comput. Imaging"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1606.07536","article-title":"Coupled generative adversarial networks","volume":"29","author":"Liu","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref37","author":"Liu","year":"2025"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.neucom.2020.12.089","article-title":"Deep learning for monocular depth estimation: a review","volume":"438","author":"Ming","year":"2021","journal-title":"Neurocomputing"},{"key":"ref39","author":"Oquab","year":"2023"},{"key":"ref40","author":"Piccinelli","year":"2024"},{"key":"ref41","author":"Radford","year":"2016"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"1677","DOI":"10.1049\/itr2.12537","article-title":"A simulation-based impact assessment of autonomous vehicles in urban networks","volume":"18","author":"Sadid","year":"2024","journal-title":"IET Intell. Transp. Syst."},{"key":"ref43","author":"Shrivastava","year":"2017"},{"key":"ref44","author":"Shubham","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tase.2025.3546713","article-title":"Neural rendering and flow-assisted unsupervised multi-view stereo for real-time monocular tracking and scene perception","volume":"1","author":"Tong","year":"","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"ref46","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1109\/tase.2023.3330704","article-title":"Edge-assisted epipolar transformer for industrial scene reconstruction","volume":"22","author":"Tong","year":"","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"ref47","doi-asserted-by":"publisher","first-page":"10761","DOI":"10.1109\/tii.2024.3392270","article-title":"Robust depth estimation based on parallax attention for aerial scene perception","volume":"20","author":"Tong","year":"2024","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref48","doi-asserted-by":"publisher","first-page":"8614","DOI":"10.1109\/TCSVT.2024.3387451","article-title":"Robust unpaired image dehazing via adversarial deformation constraint","volume":"34","author":"Wei","year":"2024","journal-title":"IEEE Trans Circ. Syst. Vid."},{"key":"ref49","doi-asserted-by":"publisher","first-page":"3141","DOI":"10.1109\/TETCI.2024.3369998","article-title":"Differentiable architecture search with attention mechanisms for generative adversarial networks","volume":"8","author":"Xue","year":"2024","journal-title":"IEEE Trans Emerg. Top. Comput. Intell."},{"key":"ref50","author":"Yang","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2024.3476560","article-title":"Destripecyclegan: stripe simulation cyclegan for unsupervised infrared image destriping","volume":"73","author":"Yang","year":"2024","journal-title":"IEEE Trans Instrum and Meas."},{"key":"ref52","doi-asserted-by":"publisher","first-page":"100250","DOI":"10.1016\/j.jnlest.2024.100250","article-title":"Data augmentation method for insulators based on cycle-Gan","volume":"22","author":"Ye","year":"2024","journal-title":"J. Electron. Sci. Technol."},{"key":"ref53","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2024.3431460","article-title":"Building cross-domain mapping chains from multi-cyclegan for hyperspectral image classification","volume":"62","author":"Ye","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref54","doi-asserted-by":"publisher","first-page":"110811","DOI":"10.1016\/j.patcog.2024.110811","article-title":"Deep generative domain adaptation with temporal relation attention mechanism for cross-user activity recognition","volume":"156","author":"Ye","year":"2024","journal-title":"Pattern Recogn."},{"key":"ref55","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2024.3432601","article-title":"Cycle-Gan network incorporated with atmospheric scattering model for dust removal of martian optical images","volume":"62","author":"Ye","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref56","doi-asserted-by":"publisher","first-page":"127873","DOI":"10.1016\/j.neucom.2024.127873","article-title":"A single-image Gan model using self-attention mechanism and densenets","volume":"596","author":"Yildiz","year":"2024","journal-title":"Neurocomputing"},{"key":"ref57","author":"Yun","year":"2019"},{"key":"ref58","author":"Zhang","year":"2024"},{"key":"ref59","author":"Zhang","year":"2024"},{"key":"ref60","doi-asserted-by":"publisher","first-page":"3071","DOI":"10.1109\/IV55156.2024.10588493","article-title":"Exploring generative ai for sim2real in driving data synthesis","author":"Zhao","year":"2024","journal-title":"IEEE Intell. Veh. Symp."},{"key":"ref61","author":"Zhu","year":"2017"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2025.1603964\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T06:11:43Z","timestamp":1748585503000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2025.1603964\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,30]]},"references-count":61,"alternative-id":["10.3389\/fnbot.2025.1603964"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2025.1603964","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,30]]},"article-number":"1603964"}}