LLLin Li

Lin Li

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Lin Li has a total of 26 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Image Aesthetics Assessment Based on GNN-Guided Deformable Attention for Electronic Photography

    by Lin Li, Jichun Zhu, Mingxing Jiang, Jingli Fang

    With the increasing demand for high-quality imaging in consumer electronics, image aesthetics assessment (IAA) has been widely applied to electronic cameras and display devices. Although the deformable attention mechanism has been introduced into IAA due to its perceptual capabilities, enabling models to refine attention regions by learning interest points and their corresponding offsets, existing methods often lack guidance from aesthetic composition features during the offset generation process, which limits their performance in aesthetic evaluation tasks. To address this issue, we propose a graph neural network (GNN)-guided deformable attention module that incorporates composition information into the generation of interest points by modeling image features as graphs and applying the GNN to guide interest point selection. In addition, we design an improved transformer model that employs neighborhood attention to further enhance IAA performance. We evaluate the proposed model on two aesthetic datasets, AVA and TAD66K, and the experimental results demonstrate its effectiveness in improving overall model performance.


  • Joint Resolution and Rendering Artifacts Removal for Cloud Gaming Image

    by Yang Zhao, Fan Fan, Yuan Chen, Lin Li, Wei Jia, Ronggang Wang

    With the rapid development of the cloud gaming industry, low-quality rendering and rescaling strategies are commonly employed to mitigate the high costs of cloud-based computation and bandwidth. As a result, client-side images often contain artifacts such as mixed aliasing and resolution distortions, which cannot be effectively handled by current super-resolution models. In response, this paper proposes a cloud gaming image enhancement (CGIE) model to tackle both rendering and resolution degradations. Initially, this paper builds a large dataset by rendering and rescaling paired data with different qualities from collected 3D game scenes. Subsequently, a lightweight dual-branch enhancement network is designed, which consists of a high-frequency branch primarily focused on detail enhancement and a sampling-space branch aimed at enlarging the receptive field and perceiving multi-scale aliasing artifacts. Experimental results demonstrate the superior anti-aliasing and image enhancement performance of the proposed method across various real-world cloud games and even mobile games. The dataset and codes are available at https://github.com/YCheno/CGIE/.

  • Open Access

    Image Aesthetic Assessment Based on GNN-Guided Deformable Attention for Electronic Photography

    by Lin Li, Jichun Zhu, Mingxing Jiang, Jingli Fang

    With the increasing demand for high-quality imaging in consumer electronics, image aesthetic assessment (IAA) has been widely applied to electronic cameras and display devices. Although the deformable attention mechanism has been introduced into IAA due to its perceptual capabilities, enabling models to refine attention regions by learning interest points and their corresponding offsets, existing methods often lack guidance from aesthetic composition features during the offset generation process, which limits their performance in aesthetic evaluation tasks. To address this issue, we propose a Graph Neural Network (GNN)-guided deformable attention module that incorporates composition information into the generation of interest points by modeling image features as graphs and applying GNN to guide interest point selection. In addition, we design an improved Transformer model that employs neighborhood attention to further enhance IAA performance. We evaluate the proposed model on two aesthetic datasets, AVA and TAD66K, and the experimental results demonstrate its effectiveness in improving overall model performance.

  • Open Access

    A Facility Layout Algorithm for Logistics Scenarios Driven by Transport Lines

    by Fulin Jiang, Lin Li, Yiming Tang, Hailong Zhang, Xiaoping Liu

    The layout of facilities in a logistics scenario involves not only the working facilities responsible for processing materials but also the transport lines responsible for transporting materials. The traditional facility layout methods do not take into account the transportation facilities nor calculate the material handling cost by Manhattan distance, thus failing to fulfill the actual requirements of industrial logistics scenarios. In this paper, a facility layout algorithm framework MOSA-FD driven by transport lines is proposed. A multi-objective simulated annealing (MOSA) algorithm is designed for both material handling cost (MHC) and transport facility cost (TFC) objectives. Then, a force-directed (FD) algorithm is applied to correct the unreasonable solutions according to the material transport lines in the logistics workshop, and a better solution is quickly obtained. Finally, by comparing the results with those of other metaheuristic multi-objective algorithms, the acceleration of the force-directed algorithm in this layout problem is demonstrated in experimental instances of different scales, and our method, compared to the MOSA algorithm, can reach optimal ratios of 36% and 80%, respectively, on the multi-objective.


  • Open Access

    An End-to-End Approach to Reconstructing 3D Model From Image Set

    by Youcheng Cai, Mingwei Cao, Lin Li, Xiaoping Liu

    Large-scale 3D reconstruction from imagery has received much attention from the computer vision community. However, recovering 3D structures from 2D images is a notoriously complex process that requires expertise with often limited results. This paper presents an end-to-end 3D reconstruction system that can produce high-quality 3D models from a set of unordered image collections. Our workflow is a typical 3D reconstruction architecture that consists of structure from motion (SFM), multi-view stereo (MVS), and surface reconstruction, and can automatically recover desirable 3D models without any interactive operations. Finally, a comprehensive experiment is conducted on several benchmark datasets to assess the presented system. Experimental results show that the presented system achieves significant improvements in reconstruction accuracy and completeness over the existing state-of-the-art approach.


  • Open Access

    A Perceptual-Based Noise-Agnostic 3D Skeleton Motion Data Refinement Network

    by Shu-Jie Li, Hai-Sheng Zhu, Li-Ping Zheng, Lin Li

    In this paper, we demonstrate a perceptual-based 3D skeleton motion data refinement method based on a bidirectional recurrent autoencoder, called BRA-P. Three main technical contributions are made by the proposed network. First, the proposed BRA-P can address noisy data with different noise types and amplitudes using one network, and this attribute makes the approach more suitable for raw motion data with heterogeneous mixed noise. Second, due to the usage of perceptual loss, which measures the difference in high-level features extracted by a pretrained perceptual autoencoder, BRA-P improves the perceptual similarity between refined motion data and clean motion data, especially for the case where the noisy data and target clean data have different topologies. Third, BRA-P further improves the bone-length consistency and smoothness of the refined motion using the perceptual autoencoder as a postprocessing network. Ablation experiments verify the effect of the three technical contributions of our approach. The results of the experiments on synthetic noise data and raw motion data captured by Kinect demonstrate that our method outperforms several state-of-the-art methods in the cleaning of mixed-noise data by one network.