arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.12308cs.CV

混合高斯泼溅用于新颖城市场景视图合成

Hybrid Gaussian Splatting for Novel Urban View Synthesis

Qualcomm AI Research(高通人工智能研究)

Mohamed Omran, Farhad Zanjani, Davide Abati, Jens Petersen, Amirhossein Habibian

AI总结:

针对RealADSim-NVS挑战赛,提出两阶段混合高斯泼溅与单步扩散模型方法,实现跨遍历街景新颖视图合成,在公开排行榜上以0.432分获第二名。

摘要:

本文描述了高通AI研究团队针对ICCV 2025 RealADSim研讨会上举办的RealADSim-NVS挑战赛所提出的解决方案。该挑战关注街景中的新颖视图合成,要求参赛者从训练遍历期间捕获的以车辆为中心的帧出发,生成从不同遍历(例如不同车道或车辆方向)观察同一城市环境的渲染结果。我们的解决方案受场景生成和生成式模拟器中混合方法的启发,该方法融合了高斯泼溅和扩散模型,由两个阶段组成:首先,我们拟合场景的3D重建,并从目标摄像机的视角渲染新颖视图。然后,我们使用专用的单步扩散模型增强生成的帧。我们讨论了在高斯原语初始化以及增强器模型微调及其训练数据整理方面所做的具体选择。我们报告了模型设计的性能,并根据PSNR、SSIM和LPIPS测量的新颖视图质量对其组件进行了消融实验。在报告测试结果的公开排行榜上,我们的方案达到了0.432的聚合分数,总体排名第二。

英文摘要:

This paper describes the Qualcomm AI Research solution to the RealADSim-NVS challenge, hosted at the RealADSim Workshop at ICCV 2025. The challenge concerns novel view synthesis in street scenes, and participants are required to generate, starting from car-centric frames captured during some training traversals, renders of the same urban environment as viewed from a different traversal (e.g. different street lane or car direction). Our solution is inspired by hybrid methods in scene generation and generative simulators merging gaussian splatting and diffusion models, and it is composed of two stages: First, we fit a 3D reconstruction of the scene and render novel views as seen from the target cameras. Then, we enhance the resulting frames with a dedicated single-step diffusion model. We discuss specific choices made in the initialization of gaussian primitives as well as the finetuning of the enhancer model and its training data curation. We report the performance of our model design and we ablate its components in terms of novel view quality as measured by PSNR, SSIM and LPIPS. On the public leaderboard reporting test results, our proposal reaches an aggregated score of 0.432, achieving the second place overall.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑