End-to-End Deep Structured Models for Drawing Crosswalks

通过VLM驱动的结构化绘图表示实现语音同步的白板生成

Speech-Synchronized Whiteboard Generation via VLM-Driven Structured Drawing Representations

本文提出首个包含24对Excalidraw演示与叙述音频的白板数据集，研究基于Qwen2-VL-7B模型通过时间戳条件化实现语音同步的绘图预测，验证了模型在跨学科领域中的泛化能力。

Mastering Sketching: Adversarial Augmentation for Structured Prediction

We present an integral framework for training sketch simplification networks that convert challenging rough sketches into clean line drawings. Our approach augments a simplification network with a discriminator network, training both networks jointly so that the discriminator network discerns whether a line drawing is a real training data or the output of the simplification network, which in turn tries to fool it. This approach has two major advantages. First, because the discriminator network learns the structure in line drawings, it encourages the output sketches of the simplification networ…

从图纸到决策：一种将2D工程图纸解析为结构化制造知识的视觉-语言混合框架

From Drawings to Decisions: A Hybrid Vision-Language Framework for Parsing 2D Engineering Drawings into Structured Manufacturing Knowledge

提出融合YOLOv11-OBB与轻量级VLM的混合框架，从2D工程图纸中检测并解析制造注释；在1,367张机械图纸上验证，Donut取得93.5% F1。

基于微调文档理解Transformer的工程图纸自动解析以实现结构化信息提取

Automated Parsing of Engineering Drawings for Structured Information Extraction Using a Fine-tuned Document Understanding Transformer

针对工程图纸信息人工提取低效、传统OCR效果不佳的问题，提出融合YOLOv11定向边界框检测与微调Donut的混合深度学习框架，在自制标注数据集上实现9类信息的结构化提取，单一模型性能更优，可助力高精度制造行业降本增效。

文档即结构化的记录：为文档识别设计原理性的归纳偏差

A document is worth a structured record: Principled inductive bias design for document recognition

本文提出将文档识别视为文档到记录的转录任务，设计结构特定的归纳偏差，通过实验展示了在复杂记录结构上的有效性，为设计更通用的文档识别系统提供指导。

Hierarchical Recurrent Attention Networks for Structured Online Maps

In this paper, we tackle the problem of online road network extraction from sparse 3D point clouds. Our method is inspired by how an annotator builds a lane graph, by first identifying how many lanes there are and then drawing each one in turn. We develop a hierarchical recurrent network that attends to initial regions of a lane boundary and traces them out completely by outputting a structured polyline. We also propose a novel differentiable loss function that measures the deviation of the edges of the ground truth polylines and their predictions. This is more suitable than distances on verti…