单模型实时输出深度、法线、分割等多任务结果，适合机器人应用。
Y-MAP-Net: Real-time depth, normals, segmentation, multi-label captioning and 2D human pose in RGB images
- Y型结构+多教师指导，轻量化设计支持实时推理。
- 一次前向计算完成深度、法线、分割、姿态和多标签描述生成。
- 适合机器人、移动端等对效率要求高的实际场景。
我们提出Y-MAP-Net，一种用于RGB图像的实时多任务学习的Y形神经网络架构。该网络在单次推理中同时预测深度、表面法线、人体姿态、语义分割并生成多标签描述。为实现此目标，采用多教师-单学生训练范式，由各任务专用的基础模型指导学习，使网络能将能力压缩到轻量级结构中，适用于实时应用场景。Y-MAP-Net展现出强泛化能力、结构简洁性与计算高效性，非常适合机器人及其他实际部署场景。代码将公开以支持后续研究。
原文摘要 · Abstract (English)
We present Y-MAP-Net, a Y-shaped neural network architecture designed for real-time multi-task learning on RGB images. Y-MAP-Net, simultaneously predicts depth, surface normals, human pose, semantic segmentation and generates multi-label captions, all from a single network evaluation. To achieve this, we adopt a multi-teacher, single-student training paradigm, where task-specific foundation models supervise the network's learning, enabling it to distill their capabilities into a lightweight architecture suitable for real-time applications. Y-MAP-Net, exhibits strong generalization, simplicity and computational efficiency, making it ideal for robotics and other practical scenarios. To support future research, we will release our code publicly.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。