Dan Li

Dan Li

Auto-generated profile, based on publicly available information

Dan Li

Huazhong University of Science and Technology, Wuhan, China

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
20 February 2025 in IEEE MultiMedia
Verified
Journal Article
Closed access
WLWenkai Liu
Wenkai Liu
TGTao Guan
Tao Guan
BZBin Zhu
Bin Zhu
LXLuoyuan Xu
Luoyuan Xu
ZSZikai Song
Zikai Song
WYWei Yang
Wei Yang
3D Gaussian Splatting (3DGS) has become a pivotal technology for 3D scene representation. However, its application to large-scale, high-resolution scenes (exceeding 4k×4k pixels) is hindered by the excessive computational and storage requirements for managing a large number of Gaussians. To address these challenges, we propose ’EfficientGS’, an advanced approach that optimizes 3DGS for high-resolution, large-scale scenes. First, we design a more selective densification to reduce the overproliferation of Gaussians. Second, we develop a pruning mechanism to remove redundant Gaussians that only serve as auxiliaries to adjacent ones. Finally, we introduce a sparse order increment strategy for Spherical Harmonics to reduce unnecessary storage. Our empirical evaluations on various datasets, including extensive 4K+ aerial images, demonstrate that ’EfficientGS’ can achieve high rendering fidelity with less computational and storage cost. Our code is available at https://github.com/wenkaier/EfficientGS.

6 January 2021 in IEEE Access
Verified
Journal Article
Open access
DLDan Li
Dan Li
SLShuang Liu
Shuang Liu
WXWeilai Xiang
Weilai Xiang
QTQiwei Tan
Qiwei Tan
KYKaicheng Yuan
Kaicheng Yuan
YHYingsong Hu
Yingsong Hu
Most of the existing visual SLAM schemes rely solely on point or line features to estimate camera trajectory. In some scenes such as texture missing or motion blurring, it’s difficult to find a sufficient number of reliable features, resulting in low positioning accuracy. To extract more features, an RPL-SLAM solution is proposed to extract point features and line features respectively. Ulteriorly, the depth information of RGBD image is used to restore the 3D information of point and line features, improving the accuracy of camera track positioning. RPL-SLAM scheme mainly includes three modules: tracking, local mapping and loop detection. Tracking module extends the application of line feature on the basis of point feature extraction and matching. A SLD line segment extraction algorithm which can eliminate the micro segments and a DBM segment matching algorithm based on word bag are proposed respectively. These two algorithms improve the matching efficiency while ensuring the matching accuracy, and effectively track and locate the camera of each frame. In the local mapping and loop detection module, the Plucker coordinates are applied to express the spatial line and define the re-projection error of the straight line, so that the back-end optimization error model of point-line fusion is unified to solve the instability problem in optimization. RPL-SLAM is tested on TUM RGBD and ICL-NUIM data set respectively, and compared with ORB-SLAM2. The result shows that RPL-SLAM can effectively improve the accuracy of pose estimation and map reconstruction while maintaining real-time performance by fusing point-line features with depth images.

14 June 2018 in EURASIP Journal on Wireless Communications and Networking
Verified
Journal Article
Open access
PDF file
LYLing Yuan
Ling Yuan
DLDan Li
Dan Li
SHSong Hu
Song Hu
With the wide application and rapid development of Intelligent Transportation System (ITS), the floating car has been widely used in the collection of traffic information, which is also very important in the application of the wireless sensor networks. In addition to the high-frequency floating car, energy-saving low-frequency floating car has attracted great attention, but the low-frequency GPS data have a poor effect on map matching. Taking consideration of the distance, direction, speed, and topology of road and vehicle, we propose a global map matching algorithm with low-frequency floating car data based on the matching path. The proposed algorithm preprocesses the floating car data and road network data to determine the potential points and sections by constructing the error region. Then, we calculate the potential matching path graph with the analysis of time and space. Finally, we can obtain the matching result by parallel computing with section division methodology. The experiment results demonstrate that the proposed map-matching algorithm can improve the running time and matching accuracy compared with the existing methods.

14 February 2020 in IEEE Access
Verified
Journal Article
Open access
SLShuang Liu
Shuang Liu
DLDan Li
Dan Li
TCTianchi Cao
Tianchi Cao
YSYuke Sun
Yuke Sun
YHYingsong Hu
Yingsong Hu
JJJunwen Ji
Junwen Ji
Recently, a variety of methods using the Generative Adversarial Network (GAN) for face editing have been proposed. However, the existing methods cannot control the editing content of the face elements according to the user-specified attributes or need to train a conditional GAN for editing tasks, which means it is difficult to add new attributes in the future. In this paper, a method to edit face attributes by editing the latent variable with the help of a pre-trained unconditional GAN and a linear classification model is proposed. In particular, face attribute editing is divided into two separate stages: Firstly, based on the optimization function, the generative model does a latent variable search to generate a high-quality face image that is similar to the input image. Secondly, by editing the latent variable of the GAN, the attribute of the generated face image can be modified indirectly, so it is almost unaffected by the training process and network structure of GAN, which means it is a flexible method for nearly all GAN network. Images of the FFHQ dataset are edited by attribute labels defined in Celeba dataset for experiments. These experiments prove that our method can edit a variety of face images that vary with race, gender, age, and camera shooting angle. The overall quality of the edited image is not inferior to the other face attribute editing method, and attribute classification for edited image shows a 92.6% attribute editing success rate of the proposed method.

1 January 2018 in Complexity
Verified
Journal Article
Open access
PDF file
LYLing Yuan
Ling Yuan
DLDan Li
Dan Li
SWShikang Wei
Shikang Wei
MWMingli Wang
Mingli Wang
It is widespread that the consumers browse relevant reviews for reference before purchasing the products when online shopping. Some stores or users may write deceptive reviews to mislead consumers into making risky purchase decisions. Existing methods of deceptive review detection did not consider the valid product review sets and classification probability of feature weights. In this research, we propose a deceptive review detection algorithm based on the target product identification and the calculation of the Metapath feature weight, noted as TM-DRD. The review dataset of target product is modeled as a heterogeneous review information network with the feature nodes. The classification method of graph is used to detect the deceptive reviews, which can improve the efficiency and accuracy of deceptive review detection due to the sparsity, imbalance of deceptive reviews, and the absence of category probability of feature weight calculation. The TM-DRD algorithm we proposed is validated on the real review dataset Yelp and compared with the SpEagle, NFC, and NetSpam algorithm. The experiment results demonstrate that the TM-DRD algorithm performs better than the other method with regard to the accuracy and efficiency.

31 July 2019 in IEEE Access
Verified
Journal Article
Open access
YHYingsong Hu
Yingsong Hu
WWWeijian Wang
Weijian Wang
DLDan Li
Dan Li
QZQingzhi Zeng
Qingzhi Zeng
YHYunfei Hu
Yunfei Hu
A novel bounding volume hierarchy (BVH) construction method based on locally dense clustering (LDC) was proposed for the low quality of BVH constructed in a complex scene with uneven distribution of primitives. The quality of the BVH was effectively improved by defining primitive density, analyzing the relation between density and traversal efficiency, selecting primitives with high density as the clustering center at the early stages of construction, and combining with top-down iterative clustering and bottom-up agglomerative clustering (AC). In order to effectively calculate primitive density, a local search strategy based on Morton coding was adopted. This strategy can quickly get approximate primitive density information through GPU. We evaluate the method and show that, in the complex building scene with uneven distribution of primitives, our method is 13% higher in traversal speed and 11% lower in surface area heuristic (SAH) cost. That means our method can improve the rendering speed of ray tracing effectively.