RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completion

2 code implementations • CVPR 2019 • Muhammad Sarmad, Hyunjoo Jenny Lee, Young Min Kim

While a GAN is unstable and hard to train, we circumvent the problem by (1) training the GAN on the latent space representation whose dimension is reduced compared to the raw point cloud input and (2) using an RL agent to find the correct input to the GAN to generate the latent space representation of the shape that best fits the current input of incomplete point cloud.

Generative Adversarial Network Reinforcement Learning (RL)