mlsanityData to 7 Oct 2026

GameIR: A Large-Scale Synthesized Ground-Truth Dataset for Image Restoration over Gaming Content

arXiv 2408.16866 ↗First posted 29 Aug 2024cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Image restoration methods like super-resolution and image synthesis have been successfully used in commercial cloud gaming products like NVIDIA's DLSS. However, restoration over gaming content is not well studied by the general public. The discrepancy is mainly caused by the lack of ground-truth gaming training data that match the test cases. Due to the unique characteristics of gaming content, the common approach of generating pseudo training data by degrading the original HR images results in inferior restoration performance. In this work, we develop GameIR, a large-scale high-quality computer-synthesized ground-truth dataset to fill in the blanks, targeting at two different applications. The first is super-resolution with deferred rendering, to support the gaming solution of rendering and transferring LR images only and restoring HR images on the client side. We provide 19200 LR-HR paired ground-truth frames coming from 640 videos rendered at 720p and 1440p for this task. The second is novel view synthesis (NVS), to support the multiview gaming solution of rendering and transferring part of the multiview frames and generating the remaining frames on the client side. This task has 57,600 HR frames from 960 videos of 160 scenes with 6 camera views. In addition to the RGB frames, the GBuffers during the deferred rendering stage are also provided, which can be used to help restoration. Furthermore, we evaluate several SOTA super-resolution algorithms and NeRF-based NVS algorithms over our dataset, which demonstrates the effectiveness of our ground-truth GameIR data in improving restoration performance for gaming content. Also, we test the method of incorporating the GBuffers as additional input information for helping super-resolution and NVS. We release our dataset and models to the general public to facilitate research on restoration methods over gaming content.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 39 of its 59 references that are in the map. First posted on arXiv 29 Aug 2024.

Builds on

39 of 59 references.

References · 39

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  3. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  4. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  5. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  6. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  7. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  8. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  9. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  10. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  11. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  12. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
27 more
  1. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  2. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  3. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  4. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
  5. 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 885
  6. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  7. 2018Residual Dense Network for Image Super-Resolutioncited by 796
  8. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 767
  9. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  10. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  11. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 596
  12. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
  13. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 514
  14. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 487
  15. 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 407
  16. 2019Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Modelcited by 400
  17. 2021Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughscited by 396
  18. 2018Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transformcited by 369
  19. 2018DVC: An End-to-end Deep Video Compression Frameworkcited by 324
  20. 2020Deep Unfolding Network for Image Super-Resolutioncited by 253
  21. 2020Component Divide-and-Conquer for Real-World Image Super-Resolutioncited by 243
  22. 2017Learning a Single Convolutional Super-Resolution Network for Multiple Degradationscited by 227
  23. 2019Blind Super-Resolution With Iterative Kernel Correctioncited by 203
  24. 2019Camera Lens Super-Resolutioncited by 56
  25. 2023PyNeRF: Pyramidal Neural Radiance Fieldscited by 16
  26. 2023Learning Image-Adaptive Codebooks for Class-Agnostic Image Restorationcited by 13
  27. 2022Image Super-Resolution with Deep Dictionarycited by 5

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025LCS: An AI-based Low-Complexity Scaler for Power-Efficient Super-Resolution of Game Contentcited by 0
  2. 2025mathttM3VIR: A Large-Scale Multi-Modality Multi-View Synthesized Benchmark Dataset for Image Restoration and Content Creationcited by 0