DLDan Li

Dan 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


Dan Li has a total of 53 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • FEAO: a feature-enhanced network for real-time ambient occlusion

    by Yiguo Lou, Jie Wen, Weijian Lou, Zaonan Tan, Weiping Sun, Dan Li

  • Top Cited Papers

    EfficientGS: Streamlining Gaussian Splatting for Large-Scale High-Resolution Scene Representation

    by Wenkai Liu, Tao Guan, Bin Zhu, Luoyuan Xu, Zikai Song, Dan Li, Yuesong Wang, 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.


  • Faster Ray Tracing through Hierarchy Cut Code

    by WeiLai Xiang, FengQi Liu, Zaonan Tan, Dan Li, PengZhan Xu, MeiZhi Liu, QiLong Kou

    We propose a novel ray reordering technique designed to accelerate the ray tracing process by encoding and sorting rays prior to traversal. Our method, called “hierarchy cut code”, involves encoding rays based on the cuts of the hierarchical acceleration structure, rather than relying solely on spatial coordinates. This approach allows for a more effective adaptation to the acceleration structure, resulting in a more reliable and efficient encoding outcome. Furthermore, our research identifies “bounding drift” as a major obstacle in achieving better acceleration effects using longer sorting keys in existing reordering methods. Fortunately, our hierarchy cut code successfully overcomes this issue, providing improved performance in ray tracing. Experimental results demonstrate the effectiveness of our approach, showing up to a 1.81 times faster secondary ray tracing compared to existing methods. These promising results highlight the potential for further enhancement in the acceleration effect of reordering techniques, warranting further exploration and research in this exciting field.


  • Use mean field theory to train a 200-layer vanilla GAN

    by Dan Li, Shuang Liu, Zhengxin Lyu, Weilai Xiang, Wei He, Fengqi Liu, Zhen Zhang

    Training a deep generative adversarial network (GAN) with hundreds or even thousands of layers is difficult. The backpropagation depth of generator is deeper than discriminator, leading it to occur vanishing/exploding gradients easily. This paper proposes a method to train deep vanilla GAN based on mean field theory. By adjusting the parameter variances and activation of the GAN, a 200-layer vanilla GAN can be trained steadily without adding any batch normalization layers or residual blocks. We demonstrate that deep GAN is very sensitive to the parameter variances $\sigma _w^2$ , $\sigma _b^2$ in the initialization scheme, and explain why hard tanh is more suitable than relu as an activation in a deep vanilla GAN. Experiments on the MNIST and Fashion-MNIST data sets validate that our method trains a deep vanilla GAN well and can produce high-quality images.


  • Open Access

    A SLAM System Based on RGBD Image and Point-Line Feature

    by Dan Li, Shuang Liu, Weilai Xiang, Qiwei Tan, Kaicheng Yuan, Zhen Zhang, 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.


  • Open Access

    GAN-Based Face Attribute Editing

    by Shuang Liu, Dan Li, Tianchi Cao, Yuke Sun, Yingsong Hu, 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.


  • Open Access

    Parallel BVH Construction Using Locally Density Clustering

    by Yingsong Hu, Weijian Wang, Dan Li, Qingzhi Zeng, 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.


  • Illumination consistency based on single low dynamic range images

    by Ling Yuan, Yingsong Hu, Dan Li, Qiwei Tan, Pengzhan Xu