[2602.24096] DiffusionHarmonizer: Bridging Neural Reconstruction and Photorealistic Simulation with Online Diffusion Enhancer

Computer Science > Computer Vision and Pattern Recognition arXiv:2602.24096 (cs) [Submitted on 27 Feb 2026] Title:DiffusionHarmonizer: Bridging Neural Reconstruction and Photorealistic Simulation with Online Diffusion Enhancer Authors:Yuxuan Zhang, Katarína Tóthová, Zian Wang, Kangxue Yin, Haithem Turki, Riccardo de Lutio, Yen-Yu Chang, Or Litany, Sanja Fidler, Zan Gojcic View a PDF of the paper titled DiffusionHarmonizer: Bridging Neural Reconstruction and Photorealistic Simulation with Online Diffusion Enhancer, by Yuxuan Zhang and 9 other authors View PDF HTML (experimental) Abstract:Simulation is essential to the development and evaluation of autonomous robots such as self-driving vehicles. Neural reconstruction is emerging as a promising solution as it enables simulating a wide variety of scenarios from real-world data alone in an automated and scalable way. However, while methods such as NeRF and 3D Gaussian Splatting can produce visually compelling results, they often exhibit artifacts particularly when rendering novel views, and fail to realistically integrate inserted dynamic objects, especially when they were captured from different scenes. To overcome these limitations, we introduce DiffusionHarmonizer, an online generative enhancement framework that transforms renderings from such imperfect scenes into temporally consistent outputs while improving their realism. At its core is a single-step temporally-conditioned enhancer that is converted from a pretrained mul...