Novel View Synthesis Under Large-Deviation Viewpoint for Autonomous Driving
Xin Ma, Jiguang Zhang, Peng Lu, Shibiao Xu, Chengwei Pan
Abstract
Novel view synthesis is a critical task in autonomous driving. Although 3D Gaussian Splatting (3D-GS) has shown success in generating novel views, it faces challenges in maintaining high-quality rendering when viewpoints deviate significantly from the training set. This difficulty primarily stems from complex lighting conditions and geometric inconsistencies in texture-less regions. To address these issues, we propose an attention-based illumination model that leverages light fields from neighboring views, enhancing the realism of synthesized images. Additionally, we propose a geometry optimization method using planar homography to improve geometric consistency in texture-less regions. Our experiments demonstrate substantial improvements in synthesis quality for large-deviation viewpoints, validating the effectiveness of our approach.
BibTeX
@article{Ma_Zhang_Lu_Xu_Pan_2025, title={Novel View Synthesis Under Large-Deviation Viewpoint for Autonomous Driving}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/32641}, DOI={10.1609/aaai.v39i6.32641}, abstractNote={Novel view synthesis is a critical task in autonomous driving. Although 3D Gaussian Splatting (3D-GS) has shown success in generating novel views, it faces challenges in maintaining high-quality rendering when viewpoints deviate significantly from the training set. This difficulty primarily stems from complex lighting conditions and geometric inconsistencies in texture-less regions. To address these issues, we propose an attention-based illumination model that leverages light fields from neighboring views, enhancing the realism of synthesized images. Additionally, we propose a geometry optimization method using planar homography to improve geometric consistency in texture-less regions. Our experiments demonstrate substantial improvements in synthesis quality for large-deviation viewpoints, validating the effectiveness of our approach.}, number={6}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Ma, Xin and Zhang, Jiguang and Lu, Peng and Xu, Shibiao and Pan, Chengwei}, year={2025}, month={Apr.}, pages={6000-6008} }