Haipeng Li

Haipeng Li

Auto-generated profile, based on publicly available information

Haipeng Li

School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 March 2024 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
HLHaipeng Li
Haipeng Li
DLDingrui Liu
Dingrui Liu
YZYu Zeng
Yu Zeng
SLShuaicheng Liu
Shuaicheng Liu
TGTao Gan
Tao Gan
BZBing Zeng
Bing Zeng
Accurate segmentation of lesions is crucial for diagnosis and treatment of early esophageal cancer (EEC). However, neither traditional nor deep learning-based methods up to today can meet the clinical requirements, with the mean Dice score - the most important metric in medical image analysis - hardly exceeding 0.75. In this paper, we present a novel deep learning approach for segmenting EEC lesions. Our method stands out for its uniqueness, as it relies solely on a single input image from a patient, forming the so-called “You-Only-Have-One" (YOHO) framework. On one hand, this “one-image-one-network" learning ensures complete patient privacy as it does not use any images from other patients as the training data. On the other hand, it avoids nearly all generalization-related problems since each trained network is applied only to the same input image itself. In particular, we can push the training to “over-fitting" as much as possible to increase the segmentation accuracy. Our technical details include an interaction with clinical doctors to utilize their expertise, a geometry-based data augmentation over a single lesion image to generate the training dataset (the biggest novelty), and an edge-enhanced UNet. We have evaluated YOHO over an EEC dataset collected by ourselves and achieved a mean Dice score of 0.888, which is much higher as compared to the existing deep-learning methods, thus representing a significant advance toward clinical applications. The code and dataset are available at: https://github.com/lhaippp/YOHO.

9 April 2024 in ACM Transactions on Graphics
Verified
Journal Article
Open access
HLHaipeng Li
Haipeng Li
HJHai Jiang
Hai Jiang
ALAo Luo
Ao Luo
PTPing Tan
Ping Tan
HFHaoqiang Fan
Haoqiang Fan
SLShuaicheng Liu
Shuaicheng Liu
Supervised homography estimation methods face a challenge due to the lack of adequate labeled training data. To address this issue, we propose DMHomo , a diffusion model-based framework for supervised homography learning. This framework generates image pairs with accurate labels, realistic image content, and realistic interval motion, ensuring that they satisfy adequate pairs. We utilize unlabeled image pairs with pseudo labels such as homography and dominant plane masks, computed from existing methods, to train a diffusion model that generates a supervised training dataset. To further enhance performance, we introduce a new probabilistic mask loss, which identifies outlier regions through supervised training, and an iterative mechanism to optimize the generative and homography models successively. Our experimental results demonstrate that DMHomo effectively overcomes the scarcity of qualified datasets in supervised homography learning and improves generalization to real-world scenes. The code and dataset are available at GitHub ( https://github.com/lhaippp/DMHomo ).

14 January 2024 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
HLHaipeng Li
Haipeng Li
KLKunming Luo
Kunming Luo
BZBing Zeng
Bing Zeng
SLShuaicheng Liu
Shuaicheng Liu

9 August 2021 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
SLShuaicheng Liu
Shuaicheng Liu
HLHaipeng Li
Haipeng Li
ZWZhengning Wang
Zhengning Wang
JWJue Wang
Jue Wang
SZShuyuan Zhu
Shuyuan Zhu
BZBing Zeng
Bing Zeng
Mobile captured images can be aligned using their gyroscope sensors. Optical image stabilizer (OIS) terminates this possibility by adjusting the images during the capturing. In this work, we propose a deep network that compensates for the motions caused by the OIS, such that the gyroscopes can be used for image alignment on the OIS cameras. To achieve this, we first record both videos and gyroscope readings with an OIS camera as training data. Then, we convert gyroscope readings into motion fields. Second, we propose an Essential Mixtures motion model for rolling shutter cameras, where an array of rotations within a frame are extracted as the ground-truth guidance. Third, we train a convolutional neural network with gyroscope motions as input to compensate for the OIS motion. Once finished, the compensation network can be applied for other scenes, where the image alignment is purely based on gyroscopes with no need for images contents, delivering strong robustness. Experiments show that our results are comparable with that of non-OIS cameras, and outperform image-based alignment results with a relatively large margin. Code and dataset is available at: https://github.com/lhaippp/DeepOIS .


14 December 2025
Verified
Conference Paper
Open access
KDKeyu Du
Keyu Du
JHJingyu Hu
Jingyu Hu
HLHaipeng Li
Haipeng Li
HXHao Xu
Hao Xu
HHHaibin Huang
Haibin Huang
SLShuaicheng Liu
Shuaicheng Liu