AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
PDF (1.8 MB)
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Research Article | Open Access | Just Accepted

VISTA+: Mesh-based single-view novel view synthesis and CAD-based foreground composition for synthetic driving-scene generation

Song Zhang1, Ruibo Wang1, Jian Li1, Wenxiu Shi1, Huiping Zhu1, Ruo Jia2, Ziyu Lin3, Haiquan Liu4( )

1 Z-one Technology Co., Ltd., Shanghai 201101, China

2 Department of Architecture and Civil Engineering, Chalmers University of Technology, Göteborg SE-41296, Sweden

3 School of Vehicle and Mobility, Tsinghua University, Beijing 100084, China

4 Tsing-AI (Shanghai) Technology Co., Ltd., Shanghai 200000, China

Show Author Information

Abstract

Synthetic data has emerged as a promising solution for alleviating data scarcity in autonomous driving, especially in cold-start and corner-case scenarios. However, existing synthetic data generation methods still face a trade-off between photorealistic fidelity and engineering scalability. This paper proposes VISTA+, a framework for synthetic driving-scene generation that combines mesh-based single-view novel view synthesis (NVS) of static backgrounds with computer-aided design (CAD)-based foreground rendering and foreground-background composition. Unlike multi-view neural reconstruction methods, VISTA+ avoids large-scale multi-view scene reconstruction, while still requiring camera calibration and source-to-target relative poses, thereby reducing engineering complexity. Specifically, we improve mesh-based background NVS by incorporating foreground inpainting, dense depth supervision, structural pretraining, and joint depth-offset prediction. Dynamic foreground objects are rendered using CAD assets under estimated environmental lighting and are then integrated with generated backgrounds through image harmonization. Experiments on KITTI and nuScenes demonstrate that VISTA+ outperforms representative single-view NVS baselines in terms of peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM). Furthermore, synthetic data generated by VISTA+ consistently improves the performance of multiple downstream three-dimensional (3D) object detection models, demonstrating the downstream utility and functional realism of the generated driving scenes.

References

【1】
【1】
 
 
Journal of Intelligent and Connected Vehicles

{{item.num}}

Comments on this article

Go to comment

< Back to all reports

Review Status: {{reviewData.commendedNum}} Commended , {{reviewData.revisionRequiredNum}} Revision Required , {{reviewData.notCommendedNum}} Not Commended Under Peer Review

Review Comment

Close
Close
Cite this article:
Zhang S, Wang R, Li J, et al. VISTA+: Mesh-based single-view novel view synthesis and CAD-based foreground composition for synthetic driving-scene generation. Journal of Intelligent and Connected Vehicles, 2026, https://doi.org/10.26599/JICV.2026.9210110

61

Views

1

Downloads

0

Crossref

0

Web of Science

0

Scopus

Received: 12 August 2026
Revised: 04 September 2026
Accepted: 27 October 2026
Available online: 19 November 2026

© The Author(s) 2026.

This is an open access article under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0, http://creativecommons.org/licenses/by/4.0/)