Bolin Song

Dr. Bolin Song

College of Artificial Intelligence, Dalian Maritime University, Dalian, Liaoning, China
orcid
Dalian Maritime University

Research Focus & Metrics

Representative Publications

View All Publications
12 February 2026 in Neurocomputing
Verified
Journal Article
Closed access
Bolin SongBolin Song
Bolin Song
YWYiyang Wang
Yiyang Wang
CZChangze Zhou
Changze Zhou

26 June 2025 in Journal of Visual Communication and Image Representation
Verified
Journal Article
Closed access
Bolin SongBolin Song
Bolin Song
YSYuanyuan Si
Yuanyuan Si
Ke LiKe Li
Ke Li

1 September 2023 in TechRxiv
Verified
Preprint
Open access
PDF file
Bolin SongBolin Song
Bolin Song
YWYiyang Wang
Yiyang Wang
DLDehao Liu
Dehao Liu
ZWZhaolin Wan
Zhaolin Wan
HLHongbo Liu
Hongbo Liu
ABAlan C. Bovik
Alan C. Bovik
Obtaining large-scale noisy/clean image pairs from the real world to train a denoising model is a difficult and cumbersome task. Self-supervised image denoisers have gained recent attention by adopting blind-spot networks to remove noise from single noisy images. However, the results of blind-spot denoisers suffer from losses of image detail caused by the selection of random masks. Here, we propose an edge-enhanced denoising approach called Self2Grad that compensates for the loss of important details when using self-supervised networks. Specifically, we develop a gradient-regularized loss function, which when added to the overall network loss acts to preserve details in images processed by blind-spot networks. In addition, we show that the loss obtained with Self2Grad is approximately equal to the loss incurred by supervised approaches. When compared to state-of-the-art (SOTA) blind-spot denoisers, Self2Grad delivers superior performance on both synthetic and real-world datasets. Indeed, Self2Grad attains comparable denoising results as methods that operate on multiple images. In particular, Self2Grad is especially effective on images corrupted by high levels of noise.

19 September 2025 in Machine Learning: Science and Technology
Verified
Journal Article
Open access
Ke LiKe Li
Ke Li
Bolin SongBolin Song
Bolin Song
NWNaiyao Wang
Naiyao Wang
ZWZhen Wang
Zhen Wang
Ruijie TianRuijie Tian
Ruijie Tian
The prediction of scene depth from monocular images has become crucial in fields such as spatial perception and computer vision. However, unsupervised depth estimation methods based on view synthesis often ignore the significant impact of non-Lambertian surfaces and ghosting artifacts. In this study, we propose a self-learning depth reconstruction framework. This framework introduces a depth consistency loss to compensate for the failure of the photometric assumption in non-Lambertian regions. Additionally, we design an intrinsic consistency loss that leverages variance as a game-theoretic strategy to ensure the robustness of our model. Finally, we introduce a physics-inspired ghosting mask to eliminate ghosting artifacts. We also design a multi-path transformer layer that integrates the Transformer’s global dependency modeling capability into CNNs, thereby enhancing the model’s performance. Experimental results show that our model demonstrates excellent performance in non-Lambertian regions. Compared with state-of-the-art methods that merely rely on the photometric assumption, our method achieves average improvements of 9.29% and 2.86% on the Sq Rel and RMSE metrics across three network models. Furthermore, it exhibits outstanding zero-shot generalization capability on external datasets. The source code is available at https://github.com/IkeFwd/Icdepth.

1 January 2025 in AIMS Mathematics
Verified
Journal Article
Open access
PDF file
Bolin SongBolin Song
Bolin Song
ZSZhenhao Shuai
Zhenhao Shuai
YSYuanyuan Si
Yuanyuan Si
Ke LiKe Li
Ke Li
Over the past few years, deep learning-based approaches have come to dominate the areas of image processing, with no exception to the field of image denoising. Recently, self-supervised denoising networks have garnered extensive attention in the zero-shot domain. Nevertheless, training the denoising network solely with zero-shot data will lead to significant detail loss, thereby influencing the denoising quality. In this work, we proposed a novel dual mask mechanism based on Euclidean distance selection as a global masker for the blind spot network, thereby enhancing image quality and mitigating image detail loss. Furthermore, we also constructed a recurrent framework, named Blind2Grad, which integrated the gradient-regularized loss and a uniform loss for training the denoiser and enabled the double-mask mechanism to be continuously updated. This framework was capable of directly acquiring information from the original noisy image, giving priority to the key information that needed to be retained without succumbing to equivalent mapping. Moreover, we conducted a thorough theoretical analysis of the convergence properties of our Blind2Grad loss from both probabilistic and game-theoretic viewpoints, demonstrating its consistency with supervised methods. Our Blind2Grad not only demonstrated outstanding performance on both synthetic and real-world datasets, but also exhibited significant efficacy in processing images with high noise levels.