We propose 3D Super Resolution (3DSR), a novel 3D Gaussian-splatting-based super-resolution framework that leverages off-the-shelf diffusion-based 2D super-resolution models. 3DSR encourages 3D consistency across views via the use of an explicit 3D Gaussian-splatting-based scene representation. This makes the proposed 3DSR different from prior work, such as image upsampling or the use of video super-resolution, which either don't consider 3D consistency or aim to incorporate 3D consistency implicitly. Notably, our method enhances visual quality without additional fine-tuning, ensuring spatial coherence within the reconstructed scene. We evaluate 3DSR on MipNeRF360 and LLFF data, demonstrating that it produces high-resolution results that are visually compelling, while maintaining structural consistency in 3D reconstructions.
@article{arxiv.2508.04090,
title = {Bridging Diffusion Models and 3D Representations: A 3D Consistent Super-Resolution Framework},
author = {Yi-Ting Chen and Ting-Hsuan Liao and Pengsheng Guo and Alexander Schwing and Jia-Bin Huang},
journal= {arXiv preprint arXiv:2508.04090},
year = {2025}
}
Comments
Accepted to ICCV 2025. Project website: https://consistent3dsr.github.io/