SRNeRF: Super-Resolution Neural Radiance Fields for Autonomous Driving Scenario Reconstruction from Sparse Views
Jun Wang, Xiaojun Zhu, Ziyu Chen, Peng Li, Chunmao Jiang, Hui Zhang, Chennian Yu, Biao Yu · World Electric Vehicle Journal · 2025
High-fidelity driving scenario reconstruction can generate a lot of realistic virtual simulation environment samples, which can support effective training and testing for autonomous vehicles. Neural radiance fields (NeRFs) have demonstrated their excellence in high-fidelity scenario reconstruction; however, they still rely on dense-view data and precise camera poses, which are difficult to obtain in autonomous vehicles. To address the above issues, we propose a novel approach called SRNeRF, which can eliminate pose-based operations and perform scenario reconstruction from sparse views. To extract more scene knowledge from limited views, we incorporate an image super-resolution module based on a fully convolutional neural network and introduce a new texture loss to capture scene details for higher-quality scene reconstruction. On both object-centric and scene-level datasets, SRNeRF performs comparably to previous methods with ground truth poses and significantly outperforms methods with predicted poses, with a PSNR improvement of about 30%. Finally, we evaluate SRNeRF on our custom autonomous driving dataset, and the results show that SRNeRF can still generate stable images and novel views in the face of sparse views, demonstrating its scalability in autonomous driving scenario synthesis.