Publication Date: 6/3/2026

Event: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2026)

Reference: pp. 24895-24905, 2026

Authors: Yifan Wang, NEC Laboratories America, Inc., Stony Brook University; Francesco Pittaluga, NEC Laboratories America, Inc.; Zaid Tasneem, NEC Laboratories America, Inc.; Chenyu You, Stony Brook University; Manmohan Chandraker, NEC Laboratories America, Inc., UC San Diego; Ziyu Jiang, NEC Laboratories America, Inc.

Abstract: Controllable driving scene generation is critical for realistic and scalable autonomous driving simulation, yet existing approaches struggle to jointly achieve photorealism and precise control. We introduce HorizonForge, a unified framework that reconstructs scenes as editable Gaussian Splats and Meshes, enabling fine-grained 3D manipulation and language-driven vehicle insertion. Edits are rendered through a noise-aware video diffusion process that enforces spatial and temporal consistency, producing diverse scene variations in a single feed-forward pass without per-trajectory optimization. To standardize evaluation, we further propose HorizonSuite, a comprehensive benchmark spanning ego- and agent-level editing tasks such as trajectory modifications and object manipulation. Extensive experiments show that Gaussian Splatting delivers substantially higher fidelity than alternative 3D representations, and that temporal priors from video diffusion are essential for coherent synthesis. Combining these findings, HorizonSuite establishes a simple yet powerful paradigm for photorealistic, controllable driving simulation, achieving an 83.4% user-preference gain and a 25.19% FID improvement over the second best state-of-the-art method. Project page: https://horizonforge.github.io/.

Publication Link: https://openaccess.thecvf.com/content/CVPR2026/html/Wang_HorizonForge_Driving_Scene_Editing_with_Any_Trajectories_and_Any_Vehicles_CVPR_2026_paper.html