# Alignment-free HDR Deghosting with Semantics Consistent Transformer

arXiv: https://arxiv.org/abs/2305.18135 · HTML: https://mlsanity.com/paper/2305.18135/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 38 references that are in the map.
- First posted on arXiv 29 May 2023.

## Builds on (most cited first, 10 of 10)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Attention-guided Network for Ghost-free High Dynamic Range Imaging](https://mlsanity.com/paper/1904.10293/) (2019)
- [HDR-GAN: HDR Image Reconstruction from Multi-Exposed LDR Images with Large Motions](https://mlsanity.com/paper/2007.01628/) (2020)
- [Ghost-free High Dynamic Range Imaging with Context-aware Transformer](https://mlsanity.com/paper/2208.05114/) (2022)
- [NTIRE 2021 Challenge on High Dynamic Range Imaging: Dataset, Methods and Results](https://mlsanity.com/paper/2106.01439/) (2021)
- [FlexHDR: Modelling Alignment and Exposure Uncertainties for Flexible HDR Imaging](https://mlsanity.com/paper/2201.02625/) (2022)
- [NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results](https://mlsanity.com/paper/2205.12633/) (2022)
- [CEN-HDR: Computationally Efficient neural Network for real-time High Dynamic Range imaging](https://mlsanity.com/paper/2302.05213/) (2023)

## Built on by (most cited first, 30 of 32)

- [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)
- [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)
- [Cinematic Gaussians: Real-Time HDR Radiance Fields with Depth of Field](https://mlsanity.com/paper/2406.07329/) (2024)
- [Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes](https://mlsanity.com/paper/2310.01840/) (2023)
- [Towards Image Ambient Lighting Normalization](https://mlsanity.com/paper/2403.18730/) (2024)
- [AIM 2025 challenge on Inverse Tone Mapping Report: Methods and Results](https://mlsanity.com/paper/2508.13479/) (2025)
- [X2HDR: HDR Image Generation in a Perceptually Uniform Space](https://mlsanity.com/paper/2602.04814/) (2026)
- [CRNet: A Detail-Preserving Network for Unified Image Restoration and Enhancement Task](https://mlsanity.com/paper/2404.14132/) (2024)
- [Bracketing Image Restoration and Enhancement with High-Low Frequency Decomposition](https://mlsanity.com/paper/2404.13537/) (2024)
- [HDRT: A Large-Scale Dataset for Infrared-Guided HDR Imaging](https://mlsanity.com/paper/2406.05475/) (2024)
- [Efficient HDR Reconstruction from Real-World Raw Images](https://mlsanity.com/paper/2306.10311/) (2023)
- [PASTA: Towards Flexible and Efficient HDR Imaging Via Progressively Aggregated Spatio-Temporal Alignment](https://mlsanity.com/paper/2403.10376/) (2024)
- [Ultra-High-Definition Dynamic Multi-Exposure Image Fusion via Infinite Pixel Learning](https://mlsanity.com/paper/2412.11685/) (2024)
- [Capturing Stable HDR Videos Using a Dual-Camera System](https://mlsanity.com/paper/2507.06593/) (2025)
- [DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models](https://mlsanity.com/paper/2604.06161/) (2026)
- [Improving Bracket Image Restoration and Enhancement with Flow-guided Alignment and Enhanced Feature Aggregation](https://mlsanity.com/paper/2404.10358/) (2024)
- [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)
- [Enabling High-Quality In-the-Wild Imaging from Severely Aberrated Metalens Bursts](https://mlsanity.com/paper/2510.10083/) (2025)
- [F2HDR: Two-Stage HDR Video Reconstruction via Flow Adapter and Physical Motion Modeling](https://mlsanity.com/paper/2603.14920/) (2026)
- [GMODiff: One-Step Gain Map Refinement with Diffusion Priors for HDR Reconstruction](https://mlsanity.com/paper/2512.16357/) (2025)
- [ExpoCM: Exposure-Aware One-Step Generative Single-Image HDR Reconstruction](https://mlsanity.com/paper/2605.02464/) (2026)
- [iHDR: Iterative HDR Imaging with Arbitrary Number of Exposures](https://mlsanity.com/paper/2505.22971/) (2025)
- [LoCAtion: Long-time Collaborative Attention Framework for High Dynamic Range Video Reconstruction](https://mlsanity.com/paper/2603.14377/) (2026)
- [Dynamic Exposure Burst Image Restoration](https://mlsanity.com/paper/2603.21784/) (2026)
- [Generating HDR Video from SDR Video](https://mlsanity.com/paper/2605.14703/) (2026)
- [HDRAgent: An Agentic Framework for Multi-Exposure HDR Imaging](https://mlsanity.com/paper/2606.09110/) (2026)
- [ExpoMotion: A Large-Scale Benchmark and A Householder Projection Network for Multi-Exposure Fusion](https://mlsanity.com/paper/2607.03110/) (2026)

## Abstract (arXiv)

High dynamic range (HDR) imaging aims to retrieve information from multiple low-dynamic range inputs to generate realistic output. The essence is to leverage the contextual information, including both dynamic and static semantics, for better image generation. Existing methods often focus on the spatial misalignment across input frames caused by the foreground and/or camera motion. However, there is no research on jointly leveraging the dynamic and static context in a simultaneous manner. To delve into this problem, we propose a novel alignment-free network with a Semantics Consistent Transformer (SCTNet) with both spatial and channel attention modules in the network. The spatial attention aims to deal with the intra-image correlation to model the dynamic motion, while the channel attention enables the inter-image intertwining to enhance the semantic consistency across frames. Aside from this, we introduce a novel realistic HDR dataset with more variations in foreground objects, environmental factors, and larger motions. Extensive comparisons on both conventional datasets and ours validate the effectiveness of our method, achieving the best trade-off on the performance and the computational cost.