Image dehazing remains a highly ill-posed problem in low-level computer vision, primarily due to the complex coupling of spatially variant haze and high-frequency background details. Existing deep learning-based methods often struggle to balance the trade-off between aggressive haze removal and the preservation of fine textures, frequently resulting in color distortion, halos, or detail loss. To address these limitations and achieve high-fidelity restoration, this paper proposes a parallel feature fusion framework driven by a haze-detail collaboration mechanism. Specifically, the proposed framework adopts a dual-branch parallel architecture to disentangle the dehazing process. The upper branch functions as a haze layer extraction network. It employs a Res2Net-based encoder to capture multi-scale semantic features and integrates a novel deformable convolution-residual hybrid attention module. By dynamically adjusting the receptive fields, this module precisely characterizes non-uniform haze distributions and models long-range dependencies. Simultaneously, the lower branch serves as a detail compensation network, leveraging context detail information blocks with multi-scale dilated convolutions to aggregate contextual cues and reinforce the representation of high-frequency textural details. Subsequently, a fusion network performs adaptive feature integration, effectively merging the extracted haze features with the enhanced detail information to reconstruct the haze-free image. To ensure robust training, a dual-supervision mechanism is introduced, combining a feature regularization loss to align feature distributions in the latent space and a reconstruction loss to constrain pixel-level content fidelity. Extensive quantitative and qualitative experiments are conducted on both synthetic benchmarks and real-world datasets. The results demonstrated that the proposed algorithm delivered superior performance, achieving higher peak signal-to-noise ratio and structural similarity scores compared to state-of-the-art methods. Visual comparisons further confirmed that our method effectively removed dense haze while recovering vivid colors and sharp structural details without introducing artifacts.
Acknowledgement
This work was supported by the Scientific Research Startup Fund for Introduced Talents of Chongqing College of Humanities, Science and Technology (No. CRKRC2025002).
Declaration of conflicting interests
The authors have no conflict of interests related to this publication.
| [1] |
ZHENG C B, YING W J, HU Q P. Comparative analysis of dehazing algorithms on real-world hazy images. Scientific Reports, 2025, 15: 10822.
|
| [2] |
HE K M, SUN J, TANG X O. Single image haze removal using dark channel prior//2009 IEEE Conference on Computer Vision and Pattern Recognition, June 20-25, 2009, Miami, FL, USA. New York: IEEE, 2009: 1956-1963.
|
| [3] |
LING P Y, CHEN H A, TAN X, et al. Single image dehazing using saturation line prior. IEEE Transactions on Image Processing, 2023, 32: 3238-3253.
|
| [4] |
LI B, HU H P, YANG Z M. Dark channel prior image dehazing algorithm based on superpixel segmentation. Journal of Test and Measurement Technology, 2025, 39(4): 415-423.
|
| [5] |
CAI B L, XU X M, JIA K, et al. DehazeNet: an end-to-end system for single image haze removal. IEEE Transactions on Image Processing, 2016, 25(11): 5187-5198.
|
| [6] |
CHEN D D, HE M M, FAN Q N, et al. Gated context aggregation network for image dehazing and deraining//2019 IEEE Winter Conference on Applications of Computer Vision, January 7-11, 2019. VillageWaikoloa, HI, USA. New York: IEEE, 2019: 1375-1383.
|
| [7] |
QIN X, WANG Z L, BAI Y C, et al. FFA-net: feature fusion attention network for single image dehazing. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(7): 11908-11915.
|
| [8] |
LUO P J, XIAO G Q, GAO X B, et al. LKD-net: large kernel convolution network for single image dehazing//2023 IEEE International Conference on Multimedia and Expo, July 10-14, 2023, Brisbane, Australia. New York: IEEE, 2023: 1601-1606.
|
| [9] |
CHEN Z X, HE Z W, LU Z M. DEA-net: single image dehazing based on detail-enhanced convolution and content-guided attention. IEEE Transactions on Image Processing, 2024, 33: 1002-1015.
|
| [10] |
HIDE R. Optics of the atmosphere: scattering by molecules and particles. Physics Bulletin, 1977, 28(11): 521.
|
| [11] |
ZHANG J L, YANG Y. Single image dehazing based on hazy features extraction and enhancement network. Journal of Measurement Science and Instrumentation, 2023, 14(1): 45-54.
|
| [12] |
JIANG K, WANG Z Y, YI P, et al. Rain-free and residue hand-in-hand: a progressive coupled network for real-time image deraining. IEEE Transactions on Image Processing, 2021, 30: 7404-7418.
|
| [13] |
GAO G H, GUO Y N, ZHOU L M, et al. Res2Net-based multi-scale and multi-attention model for traffic scene image classification. PLoS One, 2024, 19(5): e0300017.
|
| [14] |
LIU Y D, WANG X B, ZHU Y R, et al. SDCNet: spatially-adaptive deformable convolution networks for HR NonHomogeneous dehazing//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, June 17-18, 2024, Seattle, WA, USA. New York: IEEE, 2024: 6682-6691.
|
| [15] |
HUANG H, HO G T S, GEDA M W, et al. Dehaze-attention: enhancing image dehazing with a multi-scale, attention-based deep learning framework. Scientific Reports, 2025, 15: 44191.
|
| [16] |
WANG X, ZHANG S F, LIN Y Y, et al. Pixel attention convolutional network for image super-resolution. Neural Computing and Applications, 2023, 35(11): 8589-8599.
|
| [17] |
SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition. 2014: arXiv: 1409.1556.
|
| [18] |
LI B Y, REN W Q, FU D P, et al. Benchmarking single-image dehazing and beyond. IEEE Transactions on Image Processing, 2019, 28(1): 492-505.
|
| [19] |
ANCUTI C O, ANCUTI C, TIMOFTE R, et al. O-HAZE: a dehazing benchmark with real hazy and haze-free outdoor images//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, June 18-22, 2018, Salt Lake City, UT, USA. New York: IEEE, 2018: 754-762.
|
| [20] |
ANCUTI C O, ANCUTI C, TIMOFTE R. NH-HAZE: an image dehazing benchmark with non-homogeneous hazy and haze-free images//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, June 14-19, 2020. Seattle, WA, USA. New York: IEEE, 2020: 444-445.
|
PDF
(78831KB)
