MaGANSemSeg
Here is a pipeline for Fully Convolutional Refined Auto Encoding Generative Adversarial Networks for 3D Multi Object Scenes:
The codes are released here for segmentation and here for completion.
Basically, our project includes both 3D shape completion and semantic segmentation trained with the generative adversarial network.
Here is a recent survey on Indoor Scene Understanding in 2.5/3D which is published by Muzammal Naseer et al. Potential candidate for our project is expected to have look on this survey and discuss with supervisors after that as the preparation for this project.
As for practical Generative Adversarial Network techniques, here is a collection of GAN for 2D image generation tasks written in TennsorFlow and PyTorch released on Github.
| ProjectForm | |
|---|---|
| Title: | 3D Scene Semantic Segmentation Using GANs |
| Abstract: | Voxel data for indoor scenes contains different kinds of objects. Here we develop novel methods for 3D scene segmentation and refinement. Based on previous work using the generative adversarial network, we do model optimization using deep learning. Cause 3D convolutional operations consume a great amount of memory, we can design some method to reduce the amount of computational resources occupied by GPU computing. |
| Student: | |
| Director: | |
| Supervisor: | Federico Tombari, Yida Wang |
| Type: | Master Thesis |
| Area: | |
| Status: | draft |
| Start: | |
| Finish: | |
| Thesis (optional): | |
| Picture: | |