# HDRFlow: Real-Time HDR Video Reconstruction with Large Motions

arXiv: https://arxiv.org/abs/2403.03447 · HTML: https://mlsanity.com/paper/2403.03447/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 46 references that are in the map.
- First posted on arXiv 6 Mar 2024.

## Builds on (most cited first, 24 of 24)

- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [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)
- [Optical Flow Estimation using a Spatial Pyramid Network](https://mlsanity.com/paper/1611.00850/) (2016)
- [GMFlow: Learning Optical Flow via Global Matching](https://mlsanity.com/paper/2111.13680/) (2021)
- [FlowFormer: A Transformer Architecture for Optical Flow](https://mlsanity.com/paper/2203.16194/) (2022)
- [Unifying Flow, Stereo and Depth Estimation](https://mlsanity.com/paper/2211.05783/) (2022)
- [Learning to Estimate Hidden Motions with Global Motion Aggregation](https://mlsanity.com/paper/2104.02409/) (2021)
- [Iterative Geometry Encoding Volume for Stereo Matching](https://mlsanity.com/paper/2303.06615/) (2023)
- [Attention-guided Network for Ghost-free High Dynamic Range Imaging](https://mlsanity.com/paper/1904.10293/) (2019)
- [FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation](https://mlsanity.com/paper/2303.01237/) (2023)
- [Deep High Dynamic Range Imaging with Large Foreground Motions](https://mlsanity.com/paper/1711.08937/) (2017)
- [VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation](https://mlsanity.com/paper/2303.08340/) (2023)
- [LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs](https://mlsanity.com/paper/2206.10555/) (2022)
- [Ghost-free High Dynamic Range Imaging with Context-aware Transformer](https://mlsanity.com/paper/2208.05114/) (2022)
- [Accurate and Efficient Stereo Matching via Attention Concatenation Volume](https://mlsanity.com/paper/2209.12699/) (2022)
- [ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging](https://mlsanity.com/paper/2105.10697/) (2021)
- [HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Dataset](https://mlsanity.com/paper/2103.14943/) (2021)
- [Attention-Guided Progressive Neural Texture Fusion for High Dynamic Range Image Restoration](https://mlsanity.com/paper/2107.06211/) (2021)
- [A Unified Framework for Multi-Sensor HDR Video Reconstruction](https://mlsanity.com/paper/1308.4908/) (2013)
- [LAN-HDR: Luminance-based Alignment Network for High Dynamic Range Video Reconstruction](https://mlsanity.com/paper/2308.11116/) (2023)
- [A Unified HDR Imaging Method with Pixel and Patch Level](https://mlsanity.com/paper/2304.06943/) (2023)
- [Memory-Efficient Optical Flow via Radius-Distribution Orthogonal Cost Volume](https://mlsanity.com/paper/2312.03790/) (2023)

## Built on by (most cited first, 30 of 31)

- [UltraFusion: Ultra High Dynamic Imaging using Exposure Fusion](https://mlsanity.com/paper/2501.11515/) (2025)
- [Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network](https://mlsanity.com/paper/2405.00244/) (2024)
- [BANet: Bilateral Aggregation Network for Mobile Stereo Matching](https://mlsanity.com/paper/2503.03259/) (2025)
- [A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking](https://mlsanity.com/paper/2505.19858/) (2025)
- [Hybrid Cost Volume for Memory-Efficient Optical Flow](https://mlsanity.com/paper/2409.04243/) (2024)
- [Learning Efficient Meshflow and Optical Flow from Event Cameras](https://mlsanity.com/paper/2510.04111/) (2025)
- [Capturing Stable HDR Videos Using a Dual-Camera System](https://mlsanity.com/paper/2507.06593/) (2025)
- [AdaptiveAE: An Adaptive Exposure Strategy for HDR Capturing in Dynamic Scenes](https://mlsanity.com/paper/2508.13503/) (2025)
- [DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models](https://mlsanity.com/paper/2604.06161/) (2026)
- [Boosting HDR Image Reconstruction via Semantic Knowledge Transfer](https://mlsanity.com/paper/2503.15361/) (2025)
- [S2R-HDR: A Large-Scale Rendered Dataset for HDR Fusion](https://mlsanity.com/paper/2504.07667/) (2025)
- [Mono4DGS-HDR: High Dynamic Range 4D Gaussian Splatting from Alternating-exposure Monocular Videos](https://mlsanity.com/paper/2510.18489/) (2025)
- [F2HDR: Two-Stage HDR Video Reconstruction via Flow Adapter and Physical Motion Modeling](https://mlsanity.com/paper/2603.14920/) (2026)
- [HDR Video Generation via Latent Alignment with Logarithmic Encoding](https://mlsanity.com/paper/2604.11788/) (2026)
- [BAT: Learning Event-based Optical Flow with Bidirectional Adaptive Temporal Correlation](https://mlsanity.com/paper/2503.03256/) (2025)
- [DMAligner: Enhancing Image Alignment via Diffusion Model Based View Synthesis](https://mlsanity.com/paper/2602.23022/) (2026)
- [HDR-NSFF: High Dynamic Range Neural Scene Flow Fields](https://mlsanity.com/paper/2603.08313/) (2026)
- [Wavelet-Domain Masked Image Modeling for Color-Consistent HDR Video Reconstruction](https://mlsanity.com/paper/2602.07393/) (2026)
- [InstantHDR: Single-forward Gaussian Splatting Initialization for HDR 3D Reconstruction](https://mlsanity.com/paper/2603.11298/) (2026)
- [LoCAtion: Long-time Collaborative Attention Framework for High Dynamic Range Video Reconstruction](https://mlsanity.com/paper/2603.14377/) (2026)
- [FTPFusion: Frequency-Aware Infrared and Visible Video Fusion with Temporal Perturbation](https://mlsanity.com/paper/2604.01900/) (2026)
- [High-Speed Full-Color HDR Imaging via Unwrapping Modulo-Encoded Spike Streams](https://mlsanity.com/paper/2604.14632/) (2026)
- [Lucky High Dynamic Range Smartphone Imaging](https://mlsanity.com/paper/2604.19976/) (2026)
- [Generating HDR Video from SDR Video](https://mlsanity.com/paper/2605.14703/) (2026)
- [Bricker to BRACE: A Bracket Exposure RAW Dataset and Restoration Model for Flicker-Banding](https://mlsanity.com/paper/2606.29845/) (2026)
- [Coarse-to-fine Framework for Generative MEF via Implicit Neural Representation](https://mlsanity.com/paper/2607.17611/) (2026)
- [Depth-guided Multi-view Exposure Bracketing for HDR Robot Vision](https://mlsanity.com/paper/2608.16014/) (2026)
- [High Dynamic Range Video Reconstruction from Single-Exposure Raw Sequences](https://mlsanity.com/paper/2609.27274/) (2026)
- [HaRP: High Dynamic Range Photosequencing through Dual Reversed Shutter Scanning](https://mlsanity.com/paper/2609.28439/) (2026)
- [Double-stream registration with pyramid fusion for HDR video with alternating exposures](https://mlsanity.com/paper/2609.31108/) (2026)

## Abstract (arXiv)

Reconstructing High Dynamic Range (HDR) video from image sequences captured with alternating exposures is challenging, especially in the presence of large camera or object motion. Existing methods typically align low dynamic range sequences using optical flow or attention mechanism for deghosting. However, they often struggle to handle large complex motions and are computationally expensive. To address these challenges, we propose a robust and efficient flow estimator tailored for real-time HDR video reconstruction, named HDRFlow. HDRFlow has three novel designs: an HDR-domain alignment loss (HALoss), an efficient flow network with a multi-size large kernel (MLK), and a new HDR flow training scheme. The HALoss supervises our flow network to learn an HDR-oriented flow for accurate alignment in saturated and dark regions. The MLK can effectively model large motions at a negligible cost. In addition, we incorporate synthetic data, Sintel, into our training dataset, utilizing both its provided forward flow and backward flow generated by us to supervise our flow network, enhancing our performance in large motion regions. Extensive experiments demonstrate that our HDRFlow outperforms previous methods on standard benchmarks. To the best of our knowledge, HDRFlow is the first real-time HDR video reconstruction method for video sequences captured with alternating exposures, capable of processing 720p resolution inputs at 25ms.