human-3d.github.io - Human3D 🧑‍🤝‍🧑

home > domains > human-3d.github.io

Description: Human3D

human3d (1)

Example domain paragraphs

3D Segmentation of Humans in Point Clouds with Synthetic Data

TL;DR: We propose the first multi-human body-part segmentation model, called Human3D 🧑‍🤝‍🧑, that directly operates on 3D scenes. In an extensive analysis, we validate the benefits of training on synthetic data on multiple baselines and tasks. Segmenting humans in 3D indoor scenes has become increasingly important with the rise of human-centered robotics and AR/VR applications. To this end, we propose the task of joint 3D human semantic segmentation, instance segmentation and multi-human body-part segmentati

Remarkably, our approach generalizes to out-of-distribution examples. Although trained on synthetic data and real Kinect depth data, Human3D shows promising results on reconstructed point clouds scanned with an iPhone LiDAR sensor.

Links to human-3d.github.io (5)

• francisengelmann.github.io Francis Engelmann
• aycatakmaz.github.io Ayça Takmaz
• jonasschult.github.io Jonas Schult - Jonas Schult
• ikaftan.github.io Irem Kaftan
• cmakcay.github.io Mertcan Akçay