# Y-MAP-Net: Real-time depth, normals, segmentation, multi-label captioning and 2D human pose in RGB images

Source: [Y-MAP-Net: Real-time depth, normals, segmentation, multi-label captioning and 2D human pose in RGB images](<https://www.sota2.com/research/paper/68fa75c11e209131cea69bc0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:42:59.023Z

Authors: Ammar Qammaz, Nikolaos Vasilikopoulos, Iason Oikonomidis, Antonis A. Argyros

Published: 2024-11-15T16:33:59.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2411.10334>)

[PDF](<https://arxiv.org/pdf/2411.10334.pdf>)