Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
126 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Perceptual Assessment and Optimization of HDR Image Rendering (2310.12877v6)

Published 19 Oct 2023 in eess.IV and cs.CV

Abstract: High dynamic range (HDR) rendering has the ability to faithfully reproduce the wide luminance ranges in natural scenes, but how to accurately assess the rendering quality is relatively underexplored. Existing quality models are mostly designed for low dynamic range (LDR) images, and do not align well with human perception of HDR image quality. To fill this gap, we propose a family of HDR quality metrics, in which the key step is employing a simple inverse display model to decompose an HDR image into a stack of LDR images with varying exposures. Subsequently, these decomposed images are assessed through well-established LDR quality metrics. Our HDR quality models present three distinct benefits. First, they directly inherit the recent advancements of LDR quality metrics. Second, they do not rely on human perceptual data of HDR image quality for re-calibration. Third, they facilitate the alignment and prioritization of specific luminance ranges for more accurate and detailed quality assessment. Experimental results show that our HDR quality metrics consistently outperform existing models in terms of quality assessment on four HDR image quality datasets and perceptual optimization of HDR novel view synthesis.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (63)
  1. Extending quality metrics to full luminance range images. In Human Vision and Electronic Imaging XIII, pages 109–118, 2008.
  2. Mip-NeRF: A multiscale representation for anti-aliasing neural radiance fields. In IEEE International Conference on Computer Vision, pages 5855–5864, 2021.
  3. Mip-NeRF 360: Unbounded anti-aliased neural radiance fields. In IEEE Conference on Computer Vision and Pattern Recognition, pages 5460–5469, 2022.
  4. Peter G. J. Barten. Formula for the contrast sensitivity of the human eye. In Image Quality and System Performance, pages 231–238, 2003.
  5. NeRD: Neural reflectance decomposition from image collections. In IEEE International Conference on Computer Vision, pages 12684–12694, 2021.
  6. Unstructured lumigraph rendering. In Annual Conference on Computer Graphics and Interactive Techniques, pages 425–432, 2001.
  7. Normalization as a canonical neural computation. Nature Reviews Neuroscience, 13(1):51–62, 2012.
  8. MVSNeRF: Fast generalizable radiance field reconstruction from multi-view stereo. In IEEE International Conference on Computer Vision, pages 14124–14133, 2021.
  9. Hallucinated neural radiance fields in the wild. In IEEE Conference on Computer Vision and Pattern Recognition, pages 12943–12952, 2022.
  10. Scott J. Daly. Visible differences predictor: An algorithm for the assessment of image fidelity. In Human Vision, Visual Processing, and Digital Display III, pages 2–15, 1992.
  11. Image quality assessment: Unifying structure and texture similarity. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(5):2567–2581, 2022.
  12. How to cheat with metrics in single-image HDR reconstruction. In IEEE International Conference on Computer Vision Workshops, pages 3998–4007, 2021.
  13. The lumigraph. In Annual Conference on Computer Graphics and Interactive Techniques, pages 43–54, 1996.
  14. Comparison of single image HDR reconstruction methods — the caveats of quality assessment. In Annual Conference on Computer Graphics and Interactive Techniques, pages 1:1–1:8, 2022.
  15. Deep blending for free-viewpoint image-based rendering. ACM Transactions on Graphics, 37(6):257:1–257:15, 2018.
  16. Bernd Hoefflinger. High-Dynamic-Range (HDR) Vision. Springer, 2007.
  17. HDR-NeRF: High dynamic range neural radiance fields. In IEEE Conference on Computer Vision and Pattern Recognition, pages 18398–18408, 2022.
  18. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  19. Subjective quality assessment database of HDR images compressed with JPEG XT. In International Workshop on Quality of Multimedia Experience, pages 1–6, 2015.
  20. Perceptually optimized image rendering. Journal of the Optical Society of America A, 34(9):1511–1525, 2017.
  21. Light field rendering. In Annual Conference on Computer Graphics and Interactive Techniques, pages 31–42, 1996.
  22. Neural scene flow fields for space-time view synthesis of dynamic scenes. In IEEE Conference on Computer Vision and Pattern Recognition, pages 6498–6508, 2021.
  23. Editing conditional radiance fields. In IEEE International Conference on Computer Vision, pages 5773–5783, 2021.
  24. Deblur-NeRF: Neural radiance fields from blurry images. In IEEE Conference on Computer Vision and Pattern Recognition, pages 12861–12870, 2022.
  25. PU21: A novel perceptually uniform encoding for adapting existing quality metrics for HDR. In Picture Coding Symposium, pages 1–5, 2021.
  26. Visualizing high dynamic range images in a web browser. Journal of Graphics, GPU, and Game Tools, 14(1):43–53, 2009.
  27. Age-dependent prediction of visible differences in displayed images: Age-dependent prediction of visible differences. Journal of the Society for Information Display, 26:1–21, 2018.
  28. Predicting visible differences in high dynamic range images: Model and its calibration. In Human Vision and Electronic Imaging X, pages 204–214, 2005.
  29. HDR-VDP-2: A calibrated visual metric for visibility and quality predictions in all luminance conditions. ACM Transactions on Graphics, 30(4):40:1–40:14, 2011.
  30. Practical color contrast sensitivity functions for luminance levels up to 10000 cd/m2cdsuperscriptm2\rm cd/m^{2}roman_cd / roman_m start_POSTSUPERSCRIPT 2 end_POSTSUPERSCRIPT. In Color and Imaging Conference, pages 28:1–28:6, 2020.
  31. HDR-VDP-3: A multi-metric for predicting image differences, quality and contrast distortions in high dynamic range and regular content. arXiv preprint arXiv:2304.13625, 2023.
  32. NeRF in the wild: Neural radiance fields for unconstrained photo collections. In IEEE Conference on Computer Vision and Pattern Recognition, pages 7210–7219, 2021.
  33. Switch-NeRF: Learning scene decomposition with mixture of experts for large-scale neural radiance fields. In International Conference on Learning Representations, 2022.
  34. Consolidated dataset and metrics for high-dynamic-range image quality. IEEE Transactions on Multimedia, 24(67):2125–2138, 2021.
  35. NeRF: Representing scenes as neural radiance fields for view synthesis. Communications of the ACM, 65(1):99–106, 2021.
  36. NeRF in the dark: High dynamic range view synthesis from noisy raw images. In IEEE Conference on Computer Vision and Pattern Recognition, pages 16190–16199, 2022.
  37. Perceptual signal coding for more efficient usage of bit codes. SMPTE Motion Imaging Journal, 122(4):52–59, 2013.
  38. High dynamic range texture compression for graphics hardware. ACM Transactions on Graphics, 25(3):698–706, 2006.
  39. Tone mapping-based high-dynamic-range image compression: Study of optimization criterion and perceptual quality. Optical Engineering, 52(10):102008:1–102008:15, 2013.
  40. Impact of tone mapping in high dynamic range image compression. In International Workshop on Video Processing and Quality Metrics for Consumer Electronics, pages 1–7, 2014.
  41. HDR-VDP-2.2: A calibrated method for objective quality prediction of high-dynamic range and standard images. Journal of Electronic Imaging, 24(1):010501:1–010501:10, 2015a.
  42. HDR-VQM: An objective quality measure for high dynamic range video. Signal Processing: Image Communication, 35(4):46–60, 2015b.
  43. GIRAFFE: Representing scenes as compositional generative neural feature fields. In IEEE Conference on Computer Vision and Pattern Recognition, pages 11453–11464, 2021.
  44. Nerfies: Deformable neural radiance fields. In IEEE International Conference on Computer Vision, pages 5865–5874, 2021.
  45. Metrics performance comparison for color image database. In International Workshop on Video Processing and Quality Metrics for Consumer Electronics, pages 1–6, 2009.
  46. Image database TID2013: Peculiarities, results and perspectives. Signal Processing: Image Communication, 30(3):57–77, 2015.
  47. Photographic tone reproduction for digital images. ACM Transactions on Graphics, 21(3):267–276, 2002.
  48. Free view synthesis. In European Conference on Computer Vision, pages 623–640, 2020.
  49. Stable view synthesis. In IEEE Conference on Computer Vision and Pattern Recognition, pages 12211–12220, 2021.
  50. Single image HDR reconstruction using a CNN with masked features and perceptual loss. ACM Transactions on Graphics, 39(4):80:1–80:10, 2020.
  51. A statistical evaluation of recent full reference image quality assessment algorithms. IEEE Transactions on Image Processing, 15(11):3440–3451, 2006.
  52. Review of image-based rendering techniques. In Visual Communications and Image Processing, pages 2–13, 2000.
  53. Very deep convolutional networks for large-scale image recognition. In International Conference on Learning Representations, 2015.
  54. Bernard Smith. Instantaneous companding of quantized signals. The Bell System Technical Journal, 36(3):653–710, 1957.
  55. How to analyze paired comparison data. Technical report, Department of Electrical Engineering University of Washington, 2011.
  56. Performance evaluation of objective quality metrics for HDR image compression. In Applications of Digital Image Processing XXXVII, pages 78–87, 2014.
  57. A model of local adaptation. ACM Transactions on Graphics, 34(6):166:1–166:13, 2015.
  58. VQEG. Final report from the video quality experts group on the validation of objective models of video quality assessment, 2000.
  59. Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4):600–612, 2004.
  60. High-dynamic-range still-image encoding in JPEG 2000. IEEE Computer Graphics and Applications, 25(6):57–64, 2005.
  61. PixelNeRF: Neural radiance fields from one or few images. In IEEE Conference on Computer Vision and Pattern Recognition, pages 4578–4587, 2021.
  62. An extensive performance evaluation of full-reference HDR image quality metrics. Quality and User Experience, 2(5):1–16, 2017.
  63. The unreasonable effectiveness of deep features as a perceptual metric. In IEEE Conference on Computer Vision and Pattern Recognition, pages 586–595, 2018.
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now