Hybrid Gaussian Splatting for Novel Urban View Synthesis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Omran, Mohamed, Zanjani, Farhad, Abati, Davide, Petersen, Jens, Habibian, Amirhossein
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917011887489024
author Omran, Mohamed
Zanjani, Farhad
Abati, Davide
Petersen, Jens
Habibian, Amirhossein
author_facet Omran, Mohamed
Zanjani, Farhad
Abati, Davide
Petersen, Jens
Habibian, Amirhossein
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_12308
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hybrid Gaussian Splatting for Novel Urban View Synthesis
Omran, Mohamed
Zanjani, Farhad
Abati, Davide
Petersen, Jens
Habibian, Amirhossein
Computer Vision and Pattern Recognition
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.
title Hybrid Gaussian Splatting for Novel Urban View Synthesis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.12308