Jinfeng Liu¹, Lingtong Kong², Mi Zhou², Jinwei Chen², Dan Xu^1*
1HKUST, ²vivo Mobile Communication Co., Ltd

     

Demo videos are available at the project page.

• Release project page
• Release data and code

We introduce Mono4DGS-HDR, the first system for reconstructing renderable 4D high dynamic range (HDR) scenes from unposed monocular low dynamic range (LDR) videos captured with alternating exposures. To tackle such a challenging problem, we present a unified framework with two-stage optimization approach based on Gaussian Splatting. The first stage learns a video HDR Gaussian representation in orthographic camera coordinate space, eliminating the need for camera poses and enabling robust initial HDR video reconstruction. The second stage transforms video Gaussians into world space and jointly refines the world Gaussians with camera poses. Furthermore, we propose a temporal luminance regularization strategy to enhance the temporal consistency of the HDR appearance. Since our task has not been studied before, we construct a new evaluation benchmark using publicly available datasets for HDR video reconstruction. Extensive experiments demonstrate that Mono4DGS-HDR significantly outperforms alternative solutions adapted from state-of-the-art methods in both rendering quality and speed.

If you find our work helpful to your research, please cite our paper:

@inproceedings{liu2025mono4dgshdr,
      title={Mono4DGS-HDR: High Dynamic Range 4D Gaussian Splatting from Alternating-exposure Monocular Videos}, 
      author={Jinfeng Liu and Lingtong Kong and Mi Zhou and Jinwen Chen and Dan Xu},
      booktitle={ICLR},
      year={2026},
}