mlsanityData to 14 Oct 2026

S2R-HDR: A Large-Scale Rendered Dataset for HDR Fusion

arXiv 2504.07667 ↗First posted 10 Apr 2025cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

The generalization of learning-based high dynamic range (HDR) fusion is often limited by the availability of training data, as collecting large-scale HDR images from dynamic scenes is both costly and technically challenging. To address these challenges, we propose S2R-HDR, the first large-scale high-quality synthetic dataset for HDR fusion, with 24,000 HDR samples. Using Unreal Engine 5, we design a diverse set of realistic HDR scenes that encompass various dynamic elements, motion types, high dynamic range scenes, and lighting. Additionally, we develop an efficient rendering pipeline to generate realistic HDR images. To further mitigate the domain gap between synthetic and real-world data, we introduce S2R-Adapter, a domain adaptation designed to bridge this gap and enhance the generalization ability of models. Experimental results on real-world datasets demonstrate that our approach achieves state-of-the-art HDR fusion performance. Dataset and code are available at https://openimaginglab.github.io/S2R-HDR.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 47 of its 70 references that are in the map. First posted on arXiv 10 Apr 2025.

Builds on

47 of 70 references.

References · 47

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  4. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  5. 2017Adversarial Discriminative Domain Adaptationcited by 1,311
  6. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  7. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,256
  8. 2021BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelscited by 1,245
  9. 2014How transferable are features in deep neural networks?cited by 1,225
  10. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,081
  11. 2022AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognitioncited by 719
  12. 2017Video Enhancement with Task-Oriented Flowcited by 619
35 more
  1. 2017Learning multiple visual domains with residual adapterscited by 557
  2. 2022Continual Test-Time Domain Adaptationcited by 525
  3. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 522
  4. 2021VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Taskscited by 320
  5. 2018Learning Blind Video Temporal Consistencycited by 253
  6. 2020Universal Source-Free Domain Adaptationcited by 220
  7. 2023MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyondcited by 185
  8. 2021Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classificationcited by 183
  9. 2019Attention-guided Network for Ghost-free High Dynamic Range Imagingcited by 117
  10. 2023SHERF: Generalizable Human NeRF from a Single Imagecited by 88
  11. 2020HDR-GAN: HDR Image Reconstruction from Multi-Exposed LDR Images with Large Motionscited by 80
  12. 2022Ghost-free High Dynamic Range Imaging with Context-aware Transformercited by 65
  13. 2023ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptationcited by 58
  14. 2023SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modelingcited by 54
  15. 2021ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imagingcited by 51
  16. 2022Uncertainty-guided Source-free Domain Adaptationcited by 46
  17. 2021HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Datasetcited by 45
  18. 2023PrimDiffusion: Volumetric Primitives Diffusion for 3D Human Generationcited by 34
  19. 2023Towards High-quality HDR Deghosting with Conditional Diffusion Modelscited by 33
  20. 2023Alignment-free HDR Deghosting with Semantics Consistent Transformercited by 32
  21. 2024HDRFlow: Real-Time HDR Video Reconstruction with Large Motionscited by 31
  22. 2024WHAC: World-grounded Humans and Camerascited by 30
  23. 2023Exploring Sparse Visual Prompt for Domain Adaptive Dense Predictioncited by 28
  24. 2024SAFNet: Selective Alignment Fusion Network for Efficient HDR Imagingcited by 23
  25. 2025UltraFusion: Ultra High Dynamic Imaging using Exposure Fusioncited by 21
  26. 2023LAN-HDR: Luminance-based Alignment Network for High Dynamic Range Video Reconstructioncited by 18
  27. 2022FlexHDR: Modelling Alignment and Exposure Uncertainties for Flexible HDR Imagingcited by 17
  28. 2023A Unified HDR Imaging Method with Pixel and Patch Levelcited by 17
  29. 2020Learned Dual-View Reflection Removalcited by 14
  30. 2021Progressive and Selective Fusion Network for High Dynamic Range Imagingcited by 14
  31. 2024Generating Content for HDR Deghosting from Frequency Viewcited by 14
  32. 2024Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Networkcited by 14
  33. 2023In Search for a Generalizable Method for Source Free Domain Adaptationcited by 12
  34. 2023Learning a Practical SDR-to-HDRTV Up-conversion using New Dataset and Degradation Modelscited by 11
  35. 2024GTA-HDR: A Large-Scale Synthetic Dataset for HDR Image Reconstructioncited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026ExpoMotion: A Large-Scale Benchmark and A Householder Projection Network for Multi-Exposure Fusioncited by 0
  2. 2026Recurrent Dynamic Range Extensioncited by 0