Current transformer-based 3D lane detection methods typically use instance activation maps (IAM) and point-to-point loss to achieve small geometric deviations of lanes. However, these methods suffer from such lane visibility issues as wrong lane extensions and lane omissions because IAM places the lane vanishing points by mistake and loses the blurred lanes. And their performance is limited by lane continuity issues while using the point-to-point loss. In this paper, we propose a shape-preserving and surface-fitting (SPSF) network to improve the lane visibility and enhance the lane continuity. The proposed SPSF network consists of three key steps: 3D lane preliminary prediction, lane shape-preserving, and 3D lane surface-fitting. First, we design a novel transformer decoder with a mask-guided denoising block to predict preliminary 3D lanes after generating 2D lane masks. Next, after mapping the preliminary 3D lanes to 2D projected lanes, lane shapes are preserved using a two-stage mask-guided strategy to avoid the visibility issues. The two-stage mask-guided strategy includes mask-directed horizontal position adjustment and visibility correction. Finally, after fitting the surface of 3D Lanes, we improve the continuity of lanes through a surface-fitting loss. Various experiments show that our work achieves SOTA performance on two standard benchmarks.

Mask-based video lane detection methods currently have achieved promising performance. However, they generate irregular lane masks in complex scenes, resulting in inaccurate lane positioning. Diffusion models have achieved notable success in the field of image segmentation because of their ability to restore pixel-level details. In this paper, we propose a novel framework DiffLane, termed Diffusion Model-Based Lane Mask Generation for Accurate Video Lane Detection. The main idea of our work is to exploit the detail-restoring capability of diffusion models to generate high-quality lane masks. DiffLane includes the MultiFrame Fusion Enhancer (MFFE), the MultiScale De-noising Network (MSDN) and the Dynamic Lane Perception Unit (DLPU). In MFFE, the current frame is enhanced with visual information from the past two frames through global matching-based optical flow estimation. This enhanced frame serves as a condition for each denoising step. MSDN predicts noise through a multi-scale fusion strategy, enabling the diffusion model to remove noise and generate regular lane masks precisely. DLPU regresses the coefficient vectors from the generated lane masks with DSConv applied in two directions, completing the accurate video lane detection task. Extensive experiments on the VIL-100 and OpenLane-V datasets demonstrate that our method outperforms other state-of-the-art approaches.

Monocular 3D lane detection is a challenging task for autonomous driving systems. Recent advances primarily focus on one-step methods for lane detection based on front-view features, which show promising results on straight lanes. However, curved lanes are difficult to handle with one-step prediction, which performs prediction in a single leap without gradual refinement. To address this issue, we propose a novel Denoising Diffusion Model for 3D Lane Detection framework (D3L). The main idea is to leverage the progressive generation capability of the diffusion model to generate accurate 3D curved lanes, and ensuring lane continuity through curvature constraints. The framework includes three creative components: coarse-to-fine denoiser (CFD), curvature-constrained loss (CCL) and multi-sampling aggregation strategy (MSAS). In CFD, both lane-level and point-level transformer blocks are integrated to accurately denoise 3D lanes, which effectively captures both global and local features. CCL is designed to reduce deviations in lane curvature, resulting in smoother lane continuity. This loss enhances both the accuracy and geometric consistency of lane detection, especially in complex curved scenes. MSAS is proposed to select the optimal lane point-by-point from multiple candidates, thus robustness of the lane prediction is significantly improved. Extensive experiments on two popular 3D lane detection benchmarks demonstrate that our D3 L outperforms the state-of-the-art methods.

Traditional Chinese Medicine (TCM) utilizes syndrome differentiation to formulate effective herbal prescriptions for treating complex diseases. Recently, some methods leveraging knowledge graph embedding and graph neural networks have shown promising performance. However, these approaches still straggle with challenges related to data quality, including sparsity and noise in knowledge graphs, as well as imbalances between positive and negative samples in datasets, which hinder performance improvements. To address these issues, our study introduces a novel approach integrating the Diffusion-Augmented Knowledge Graph Embedding and Graph Convolutional Network (GCN) with Asymmetric Loss (ASL). Firstly, we enhance herb representation by combining the Diffusion model with knowledge graph embedding to effectively mitigate noise and sparsity issues inherent in the knowledge graph. Then, we construct a TCM symptom-herb bipartite graph based on the dataset and employ a two-layer Bipartite Graph Convolutional Neural Network (Bipar GCN) to obtain feature embeddings. To tackle the imbalance between positive and negative samples, we introduce ASL to optimize the model. Finally, we aggregate symptom embeddings using MLP to derive a syndrome embedding, which is then multiplied with herb embeddings to compute prediction scores. Evaluated on a TCM prescription benchmark, our method outperforms others in Precision, Recall, and NDCG metrics, marking significant improvements in TCM prescription recommendation.

Although traditional Chinese medicine (TCM) and modern medicine (MM) have considerably different treatment philosophies, they both make important contributions to human health care. TCM physicians usually treat diseases using TCM formula (TCMF), which is a combination of specific herbs, based on the holistic philosophy of TCM, whereas MM physicians treat diseases using chemical drugs that interact with specific biological molecules. The difference between the holistic view of TCM and the atomistic view of MM hinders their combination. Tools that are able to bridge together TCM and MM are essential for promoting the combination of these disciplines. In this paper, we present TCMFVis, a visual analytics system that would help domain experts explore the potential use of TCMFs in MM at the molecular level. TCMFVis deals with two significant challenges, namely, (i) intuitively obtaining valuable insights from heterogeneous data involved in TCMFs and (ii) efficiently identifying the common features among a cluster of TCMFs. In this study, a four-level (herb-ingredient-target-disease) visual analytics framework was designed to facilitate the analysis of heterogeneous data in a proper workflow. Several set visualization techniques were first introduced into the system to facilitate the identification of common features among TCMFs. Case studies on two groups of TCMFs clustered by function were conducted by domain experts to evaluate TCMFVis. The results of these case studies demonstrate the usability and scalability of the system.