# Ghost-free High Dynamic Range Imaging with Context-aware Transformer

arXiv: https://arxiv.org/abs/2208.05114 · HTML: https://mlsanity.com/paper/2208.05114/

## Key facts

- Cited by 65 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 43 references that are in the map.
- First posted on arXiv 10 Aug 2022.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Pre-Trained Image Processing Transformer](https://mlsanity.com/paper/2012.00364/) (2020)
- [Image Inpainting for Irregular Holes Using Partial Convolutions](https://mlsanity.com/paper/1804.07723/) (2018)
- [Intriguing Properties of Vision Transformers](https://mlsanity.com/paper/2105.10497/) (2021)
- [Early Convolutions Help Transformers See Better](https://mlsanity.com/paper/2106.14881/) (2021)
- [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)
- [HDR-GAN: HDR Image Reconstruction from Multi-Exposed LDR Images with Large Motions](https://mlsanity.com/paper/2007.01628/) (2020)
- [DeepFuse: A Deep Unsupervised Approach for Exposure Fusion with Extreme Exposure Image Pairs](https://mlsanity.com/paper/1712.07384/) (2017)
- [ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging](https://mlsanity.com/paper/2105.10697/) (2021)

## Built on by (most cited first, 30 of 65)

- [HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting](https://mlsanity.com/paper/2405.15125/) (2024)
- [Alignment-free HDR Deghosting with Semantics Consistent Transformer](https://mlsanity.com/paper/2305.18135/) (2023)
- [HDRFlow: Real-Time HDR Video Reconstruction with Large Motions](https://mlsanity.com/paper/2403.03447/) (2024)
- [LEDiff: Latent Exposure Diffusion for HDR Generation](https://mlsanity.com/paper/2412.14456/) (2024)
- [UltraFusion: Ultra High Dynamic Imaging using Exposure Fusion](https://mlsanity.com/paper/2501.11515/) (2025)
- [A Unified HDR Imaging Method with Pixel and Patch Level](https://mlsanity.com/paper/2304.06943/) (2023)
- [Mutual-Guided Dynamic Network for Image Fusion](https://mlsanity.com/paper/2308.12538/) (2023)
- [Generating Content for HDR Deghosting from Frequency View](https://mlsanity.com/paper/2404.00849/) (2024)
- [Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network](https://mlsanity.com/paper/2405.00244/) (2024)
- [Self-Supervised Image Denoising for Real-World Images with Context-aware Transformer](https://mlsanity.com/paper/2304.01627/) (2023)
- [Cinematic Gaussians: Real-Time HDR Radiance Fields with Depth of Field](https://mlsanity.com/paper/2406.07329/) (2024)
- [Semi-supervised Deep Large-baseline Homography Estimation with Progressive Equivalence Constraint](https://mlsanity.com/paper/2212.02763/) (2022)
- [Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes](https://mlsanity.com/paper/2310.01840/) (2023)
- [GaussHDR: High Dynamic Range Gaussian Splatting via Learning Unified 3D and 2D Local Tone Mapping](https://mlsanity.com/paper/2503.10143/) (2025)
- [X2HDR: HDR Image Generation in a Perceptually Uniform Space](https://mlsanity.com/paper/2602.04814/) (2026)
- [Supervised Homography Learning with Realistic Dataset Generation](https://mlsanity.com/paper/2307.15353/) (2023)
- [CRNet: A Detail-Preserving Network for Unified Image Restoration and Enhancement Task](https://mlsanity.com/paper/2404.14132/) (2024)
- [Diffusion-Promoted HDR Video Reconstruction](https://mlsanity.com/paper/2406.08204/) (2024)
- [HDRT: A Large-Scale Dataset for Infrared-Guided HDR Imaging](https://mlsanity.com/paper/2406.05475/) (2024)
- [Learning Efficient Meshflow and Optical Flow from Event Cameras](https://mlsanity.com/paper/2510.04111/) (2025)
- [BurstDeflicker: A Benchmark Dataset for Flicker Removal in Dynamic Scenes](https://mlsanity.com/paper/2510.09996/) (2025)
- [It Takes Two: A Duet of Periodicity and Directionality for Burst Flicker Removal](https://mlsanity.com/paper/2603.22794/) (2026)
- [High Dynamic Range Imaging with Context-aware Transformer](https://mlsanity.com/paper/2304.04416/) (2023)
- [Efficient HDR Reconstruction from Real-World Raw Images](https://mlsanity.com/paper/2306.10311/) (2023)
- [IFT: Image Fusion Transformer for Ghost-free High Dynamic Range Imaging](https://mlsanity.com/paper/2309.15019/) (2023)
- [Single-Image HDR Reconstruction Assisted Ghost Suppression and Detail Preservation Network for Multi-Exposure HDR Imaging](https://mlsanity.com/paper/2403.04228/) (2024)
- [PASTA: Towards Flexible and Efficient HDR Imaging Via Progressively Aggregated Spatio-Temporal Alignment](https://mlsanity.com/paper/2403.10376/) (2024)
- [Sagiri: Low Dynamic Range Image Enhancement with Generative Diffusion Prior](https://mlsanity.com/paper/2406.09389/) (2024)
- [Rethinking Theoretical Illumination for Efficient Low-Light Image Enhancement](https://mlsanity.com/paper/2409.05274/) (2024)
- [Ultra-High-Definition Dynamic Multi-Exposure Image Fusion via Infinite Pixel Learning](https://mlsanity.com/paper/2412.11685/) (2024)

## Abstract (arXiv)

High dynamic range (HDR) deghosting algorithms aim to generate ghost-free HDR images with realistic details. Restricted by the locality of the receptive field, existing CNN-based methods are typically prone to producing ghosting artifacts and intensity distortions in the presence of large motion and severe saturation. In this paper, we propose a novel Context-Aware Vision Transformer (CA-ViT) for ghost-free high dynamic range imaging. The CA-ViT is designed as a dual-branch architecture, which can jointly capture both global and local dependencies. Specifically, the global branch employs a window-based Transformer encoder to model long-range object movements and intensity variations to solve ghosting. For the local branch, we design a local context extractor (LCE) to capture short-range image features and use the channel attention mechanism to select informative local details across the extracted features to complement the global branch. By incorporating the CA-ViT as basic components, we further build the HDR-Transformer, a hierarchical network to reconstruct high-quality ghost-free HDR images. Extensive experiments on three benchmark datasets show that our approach outperforms state-of-the-art methods qualitatively and quantitatively with considerably reduced computational budgets. Codes are available at https://github.com/megvii-research/HDR-Transformer