# Double-stream registration with pyramid fusion for HDR video with alternating exposures

arXiv: https://arxiv.org/abs/2609.31108 · HTML: https://mlsanity.com/paper/2609.31108/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 26 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Builds on (most cited first, 12 of 12)

- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [Softmax Splatting for Video Frame Interpolation](https://mlsanity.com/paper/2003.05534/) (2020)
- [Deep High Dynamic Range Imaging with Large Foreground Motions](https://mlsanity.com/paper/1711.08937/) (2017)
- [Ghost-free High Dynamic Range Imaging with Context-aware Transformer](https://mlsanity.com/paper/2208.05114/) (2022)
- [Residual Conv-Deconv Grid Network for Semantic Segmentation](https://mlsanity.com/paper/1707.07958/) (2017)
- [HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Dataset](https://mlsanity.com/paper/2103.14943/) (2021)
- [HDRFlow: Real-Time HDR Video Reconstruction with Large Motions](https://mlsanity.com/paper/2403.03447/) (2024)
- [LAN-HDR: Luminance-based Alignment Network for High Dynamic Range Video Reconstruction](https://mlsanity.com/paper/2308.11116/) (2023)
- [A Maximum A Posteriori Estimation Framework for Robust High Dynamic Range Video Synthesis](https://mlsanity.com/paper/1612.02761/) (2016)
- [Exposure Completing for Temporally Consistent Neural High Dynamic Range Video Rendering](https://mlsanity.com/paper/2407.13309/) (2024)
- [F2HDR: Two-Stage HDR Video Reconstruction via Flow Adapter and Physical Motion Modeling](https://mlsanity.com/paper/2603.14920/) (2026)

## Abstract (arXiv)

High dynamic range (HDR) video reconstruction from al-ter-na-ting-exposure sequences remains challenging, especially in regions with extreme luminance variation. We propose a novel HDR reconstruction framework based on dual-stream registration and accurate pyramid fusion. Given three consecutive frames, our method computes optical flow directly with the central frame, while introducing a complementary midpoint displacement strategy to handle cases with severe overexposition. A pyramid fusion stage then merges the resulting radiance and LDR images into a final HDR output. Experimental results demonstrate that our approach consistently outperforms state-of-the-art methods.