Unsupervised Low-Light Image Enhancement Based on Explicit Denoising and Knowledge Distillation
Source abstract
Abstract
Under low-illumination conditions, the quality of image signals deteriorates significantly, typically characterized by a peak signal-to-noise ratio (PSNR) below 10 dB, which severely limits the usability of the images. Superv... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Image Enhancement Techniques · Image and Signal Denoising Methods · Advanced Image Fusion Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (45)
Show source-provided references
1. Low-light image enhancement for autonomous driving systems using DriveretiNex-Net
2. C. Wei et al., “Deep retinex decomposition for low-light enhancement,” 2018, arXiv:1808.04560.
3. STAR: A structure and texture aware retinex model10.1109/TIP.2020.2974060 ↗
4. Learning a deep single image contrast enhancer from multi-exposure images10.1109/TIP.2018.2794218 ↗
5. Learning a simple low-light image enhancer from paired low-light instances
6. Self-guided network for fast image denoising
7. Low-light image enhancement with semi-decoupled decomposition10.1109/TMM.2020.2969790 ↗
8. Zero-reference deep curve estimation for low-light image enhancement
9. Learning optimized low-light image enhancement for edge vision tasks
10. EnlightenGAN: Deep light enhancement without paired supervision10.1109/TIP.2021.3051462 ↗
11. Learning with privileged information for efficient image super-resolution
12. Image quality enhancement with applications to unmanned aerial vehicle obstacle detection10.3390/aerospace9120829 ↗
13. Y. Zhu, L. Wang, J. Yuan, and Y. Guo, “Diffusion model based low-light image enhancement for space satellite,” 2023, arXiv:2306.14227.
14. A survey on image enhancement for low-light images
15. Matching in the dark: A dataset for matching image pairs of low-light scenes
16. LLNet: A deep autoencoder approach to natural low-light image enhancement10.1016/j.patcog.2016.06.008 ↗
17. Lv · Brit. Mach. Vis. Conf. · 2018
18. LightenNet: A convolutional neural network for weakly illuminated image enhancement10.1016/j.patrec.2018.01.010 ↗
19. Learning to see in the dark
20. A contrast enhancement method using dynamic range separate histogram equalization10.1109/TCE.2008.4711262 ↗
21. Contrast enhancement based on layered difference representation of 2D histograms10.1109/TIP.2013.2284059 ↗
22. LIME: Low-light image enhancement via illumination map estimation10.1109/TIP.2016.2639450 ↗
23. Structure-revealing low-light image enhancement via robust retinex model10.1109/TIP.2018.2810539 ↗
24. Uretinex-Net: Retinex-based deep unfolding network for low-light image enhancement
25. SNR-aware low-light image enhancement
26. Deep color consistent network for low-light image enhancement
27. Retinex-inspired unrolling with cooperative prior architecture search for low-light image enhancement
28. Implicit neural representation for cooperative low-light image enhancement
29. FeatEnHancer: Enhancing hierarchical features for object detection and beyond under low-light vision
30. G. Hinton, O. Vinyals, and J. Dean, “Distilling the knowledge in a neural network,” 2015, arXiv:1503.02531.
31. T. Chen, I. Goodfellow, and J. Shlens, “Net2Net: Accelerating learning via knowledge transfer,” 2015, arXiv:1511.05641.
32. Be your own teacher: Improve the performance of convolutional neural networks via self distillation
33. S. Zagoruyko and N. Komodakis, “Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer,” 2016, arXiv:1612.03928.
34. Structured knowledge distillation for semantic segmentation
35. Image super-resolution using knowledge distillation
36. Fakd: Feature-affinity based knowledge distillation for efficient image super-resolution10.1109/ICIP40778.2020.9190917 ↗
37. Low-light image enhancement with knowledge distillation10.1016/j.neucom.2022.10.083 ↗
38. D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” 2014, arXiv:1412.6980.
39. Image quality assessment: From error visibility to structural similarity10.1109/TIP.2003.819861 ↗
40. The unreasonable effectiveness of deep features as a perceptual metric
41. The ciede2000 color-difference formula: Implementation notes, supplementary test data, and mathematical observations10.1002/col.20070 ↗
42. GLADNet: Low-light enhancement network with global awareness
43. Kindling the darkness: A practical low-light image enhancer
44. Zero-shot restoration of underexposed images via robust retinex decomposition
45. Toward fast, flexible, and robust low-light image enhancement