Improved Adversarial Systems for 3D Object Generation and Reconstruction
This work addresses the challenge of generating and reconstructing 3D objects from 2D images or incomplete scans, which is incremental as it extends previous methods with a modified training objective.
The paper tackled the problem of training generative adversarial networks (GANs) for 3D object generation and reconstruction, achieving notable quantitative improvements over existing baselines.
This paper describes a new approach for training generative adversarial networks (GAN) to understand the detailed 3D shape of objects. While GANs have been used in this domain previously, they are notoriously hard to train, especially for the complex joint data distribution over 3D objects of many categories and orientations. Our method extends previous work by employing the Wasserstein distance normalized with gradient penalization as a training objective. This enables improved generation from the joint object shape distribution. Our system can also reconstruct 3D shape from 2D images and perform shape completion from occluded 2.5D range scans. We achieve notable quantitative improvements in comparison to existing baselines