# HDR Video Reconstruction with Tri-Exposure Quad-Bayer Sensors

arXiv: https://arxiv.org/abs/2103.10982 · HTML: https://mlsanity.com/paper/2103.10982/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 42 references that are in the map.
- First posted on arXiv 19 Mar 2021.

## Builds on (most cited first, 13 of 13)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation](https://mlsanity.com/paper/1712.00080/) (2017)
- [FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation](https://mlsanity.com/paper/1907.01361/) (2019)
- [Attention-guided Network for Ghost-free High Dynamic Range Imaging](https://mlsanity.com/paper/1904.10293/) (2019)
- [Deep High Dynamic Range Imaging with Large Foreground Motions](https://mlsanity.com/paper/1711.08937/) (2017)
- [DVDnet: A Fast Network for Deep Video Denoising](https://mlsanity.com/paper/1906.11890/) (2019)
- [Handheld Mobile Photography in Very Low Light](https://mlsanity.com/paper/1910.11336/) (2019)
- [Deep Burst Denoising](https://mlsanity.com/paper/1712.05790/) (2017)
- [Convolutional Sparse Coding for High Dynamic Range Imaging](https://mlsanity.com/paper/1806.04942/) (2018)
- [Gated Fusion Network for Joint Image Deblurring and Super-Resolution](https://mlsanity.com/paper/1807.10806/) (2018)
- [Evaluating the Performance of Existing Full-Reference Quality Metrics on High Dynamic Range (HDR) Video Content](https://mlsanity.com/paper/1803.04815/) (2018)

## Built on by (most cited first, 13 of 13)

- [Deep Learning for HDR Imaging: State-of-the-Art and Future Trends](https://mlsanity.com/paper/2110.10394/) (2021)
- [LAN-HDR: Luminance-based Alignment Network for High Dynamic Range Video Reconstruction](https://mlsanity.com/paper/2308.11116/) (2023)
- [Learning Spatially Varying Pixel Exposures for Motion Deblurring](https://mlsanity.com/paper/2204.07267/) (2022)
- [SoDaCam: Software-defined Cameras via Single-Photon Imaging](https://mlsanity.com/paper/2309.00066/) (2023)
- [MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging](https://mlsanity.com/paper/2410.14214/) (2024)
- [HDR Video Reconstruction with a Large Dynamic Dataset in Raw and sRGB Domains](https://mlsanity.com/paper/2304.04773/) (2023)
- [Spatially Varying Exposure with 2-by-2 Multiplexing: Optimality and Universality](https://mlsanity.com/paper/2306.17367/) (2023)
- [Capturing Stable HDR Videos Using a Dual-Camera System](https://mlsanity.com/paper/2507.06593/) (2025)
- [Modeling Dual-Exposure Quad-Bayer Patterns for Joint Denoising and Deblurring](https://mlsanity.com/paper/2412.07256/) (2024)
- [Video frame interpolation for high dynamic range sequences captured with dual-exposure sensors](https://mlsanity.com/paper/2206.09485/) (2022)
- [Pix2HDR -- A pixel-wise acquisition and deep learning-based synthesis approach for high-speed HDR videos](https://mlsanity.com/paper/2310.16139/) (2023)
- [A High Resolution Multi-exposure Stereoscopic Image & Video Database of Natural Scenes](https://mlsanity.com/paper/2206.11095/) (2022)
- [LoCAtion: Long-time Collaborative Attention Framework for High Dynamic Range Video Reconstruction](https://mlsanity.com/paper/2603.14377/) (2026)

## Abstract (arXiv)

We propose a novel high dynamic range (HDR) video reconstruction method with new tri-exposure quad-bayer sensors. Thanks to the larger number of exposure sets and their spatially uniform deployment over a frame, they are more robust to noise and spatial artifacts than previous spatially varying exposure (SVE) HDR video methods. Nonetheless, the motion blur from longer exposures, the noise from short exposures, and inherent spatial artifacts of the SVE methods remain huge obstacles. Additionally, temporal coherence must be taken into account for the stability of video reconstruction. To tackle these challenges, we introduce a novel network architecture that divides-and-conquers these problems. In order to better adapt the network to the large dynamic range, we also propose LDR-reconstruction loss that takes equal contributions from both the highlighted and the shaded pixels of HDR frames. Through a series of comparisons and ablation studies, we show that the tri-exposure quad-bayer with our solution is more optimal to capture than previous reconstruction methods, particularly for the scenes with larger dynamic range and objects with motion.