HFGS: 4D Gaussian Splatting with Emphasis on Spatial and Temporal High-Frequency Components for Endoscopic Scene Reconstruction


Haoyu Zhao (Wuhan University), Xingyue Zhao (Xi'an Jiaotong University), Lingting Zhu (The University of Hong Kong), Weixi Zheng (Wuhan University), Yongchao Xu (Wuhan University)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)Supplementary

Abstract

Robot-assisted minimally invasive surgery benefits from enhancing dynamic scene reconstruction, as it improves surgical outcomes. While Neural Radiance Fields (NeRF) have been effective in scene reconstruction, their slow inference speeds and lengthy training durations limit their applicability. To overcome these limitations, 3D Gaussian Splatting (3D-GS) based methods have emerged as a recent trend, offering rapid inference capabilities and superior 3D quality. However, these methods still struggle with under-reconstruction in both static and dynamic scenes. In this paper, we propose HFGS, a novel approach for deformable endoscopic reconstruction that addresses these challenges from spatial and temporal frequency perspectives. Our approach incorporates deformation fields to better handle dynamic scenes and introduces Spatial High-Frequency Emphasis Reconstruction (SHF) to minimize discrepancies in spatial frequency spectra between the rendered image and its ground truth. Additionally, we introduce Temporal High-Frequency Emphasis Reconstruction (THF) to enhance dynamic awareness in neural rendering by leveraging flow priors, focusing optimization on motion-intensive parts. Extensive experiments on two widely used benchmarks demonstrate that HFGS achieves superior rendering quality. Source code is available at https://github.com/zhaohaoyu376/HFGS.

Citation

@inproceedings{Zhao_2024_BMVC,
author    = {Haoyu Zhao and Xingyue Zhao and Lingting Zhu and Weixi Zheng and Yongchao Xu},
title     = {HFGS: 4D Gaussian Splatting with Emphasis on Spatial and Temporal High-Frequency Components for Endoscopic Scene Reconstruction},
booktitle = {35th British Machine Vision Conference 2024, {BMVC} 2024, Glasgow, UK, November 25-28, 2024},
publisher = {BMVA},
year      = {2024},
url       = {https://papers.bmvc2024.org/0039.pdf}
}


Copyright © 2024 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection