{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T00:31:10Z","timestamp":1759365070326,"version":"build-2065373602"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3613054","type":"journal-article","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T17:45:39Z","timestamp":1758563139000},"page":"166740-166759","source":"Crossref","is-referenced-by-count":0,"title":["Joint Camera-LiDAR Scene Synthesis and Perception for Autonomous Driving"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2733-3916","authenticated-orcid":false,"given":"S.","family":"Raghavendra","sequence":"first","affiliation":[{"name":"Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1119-4782","authenticated-orcid":false,"given":"S. K.","family":"Abhilash","sequence":"additional","affiliation":[{"name":"KPIT Technologies, Bengaluru, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0078-5050","authenticated-orcid":false,"given":"Venu","family":"Madhav Nookala","sequence":"additional","affiliation":[{"name":"KPIT Technologies, Bengaluru, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6808-5722","authenticated-orcid":false,"given":"P. V.","family":"Arun Kumar","sequence":"additional","affiliation":[{"name":"KPIT Technologies, Bengaluru, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6082-391X","authenticated-orcid":false,"given":"B. N.","family":"Anoop","sequence":"additional","affiliation":[{"name":"Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0237-2444","authenticated-orcid":false,"family":"Ramyashree","sequence":"additional","affiliation":[{"name":"Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3368234"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73229-4_27"},{"key":"ref3","article-title":"BEVControl: Accurately controlling street-view elements with multi-perspective consistency via BEV sketch layout","author":"Yang","year":"2023","journal-title":"arXiv:2308.01661"},{"key":"ref4","article-title":"DriveDreamer: Towards real-world-driven world models for autonomous driving","author":"Wang","year":"2023","journal-title":"arXiv:2309.09777"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00659"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_10"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_19"},{"key":"ref8","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. 33rd Int. Conf. Mach. Learn. (ICML)","author":"Reed"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref12","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Ramesh"},{"key":"ref13","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00278"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00613"},{"key":"ref17","first-page":"613","article-title":"Generating videos with scene dynamics","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Vondrick"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref19","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"1","author":"Chen"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00649"},{"key":"ref21","first-page":"9359","article-title":"Towards a unified framework for text-to-video generation","volume-title":"Proc. AAAI Conf. Artif. Intell. (AAAI)","author":"Zhou"},{"key":"ref22","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Ho"},{"key":"ref23","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Nichol"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref26","first-page":"1","article-title":"An image is Worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref29","first-page":"12860","article-title":"Mask2Former: Mask transformer for unified image and video segmentation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Cheng"},{"key":"ref30","first-page":"25166","article-title":"DatasetDM: Synthesizing data with perception annotations using diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Wu"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_2"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01396"},{"key":"ref33","article-title":"SG-LDM: Semantic-guided LiDAR generation via latent-aligned diffusion","author":"Xiang","year":"2025","journal-title":"arXiv:2506.23606"},{"key":"ref34","article-title":"Attention GhostUNet++: Enhanced segmentation of adipose tissue and liver in CT images","author":"Hayat","year":"2025","journal-title":"arXiv:2504.11491"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IEMECON62401.2024.10846748"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11175421.pdf?arnumber=11175421","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T05:19:31Z","timestamp":1759295971000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11175421\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3613054","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}