CasualHDRSplat: Robust High Dynamic Range 3D Gaussian Splatting from Casually Captured Videos

arXiv 2024

Shucheng Gong1,2*    Lingzhe Zhao1*    Wenpu Li1*    Xiang Liu1,3   
Yin Zhang1,4    Shiyu Zhao1    Hong Xie2    Peidong Liu1†

*equal contribution    † denotes corresponding author.

1Westlake University    2Wuhan University    3ETH Zürich    4Zhejiang University   

arXiv Code

Given a casually captured video with auto exposure, camera motion blur, and significant exposure time changes, we train 3DGS to reconstruct a sharp HDR scene.

After reconstructing the 3D HDR scene, we can render sharp LDR videos (for standard monitor display) with any given exposure time and camera trajectory.

Keywords

Gaussian Splatting, Deblurring, High Dynamic Range, 3D Reconstruction, Pose Estimation, Bundle Adjustment, Motion Blur, Continuous-time Trajectory

Teaser

overview

a) Our method can reconstruct 3D HDR scenes from videos casually captured with auto-exposure enabled.

b) Our approach achieves superior rendering quality compared to methods like Gaussian-W and HDR-Plenoxels.

c) After 3D HDR reconstruction, we can not only synthesize novel view, but also perform various downstream tasks, such as 1) HDR exposure editing, 2) Image deblurring.

Pipeline

overview

Given a casually captured video with auto exposure, camera motion blur, and significant exposure time changes, we train 3DGS to reconstruct an HDR scene.

We design a unified model based on the physical image formation process, integrating camera motion blur and exposure-induced brightness variations.

This allows for the joint estimation of camera motion, exposure time, and camera response curve while reconstructing the HDR scene.

After training, our method can sharpen the train images and render HDR and LDR images from specified poses.

BibTeX

@article{gong2025casualhdr,
      title={{CasualHDRSplat: Robust High Dynamic Range 3D Gaussian Splatting from Casually Captured Videos}},
      author={Gong, Shucheng and Zhao, Lingzhe and Li, Wenpu and Xie, Hong and Zhang, Yin and Zhao, Shiyu and Liu, Peidong},
      year={2025},
      eprint={2504.17728},
      archivePrefix={arXiv},
  }