3D car shape reconstruction from a contour sketch using GAN and lazy learning

Abstract

Abstract3D car models are heavily used in computer games, visual effects, and even automotive designs. As a result, producing such models with minimal labour costs is increasingly more important. To tackle the challenge, we propose a novel system to reconstruct a 3D car using a single sketch image. The system learns from a synthetic database of 3D car models and their corresponding 2D contour sketches and segmentation masks, allowing effective training with minimal data collection cost. The core of the system is a machine learning pipeline that combines the use of a generative adversarial network (GAN) and lazy learning. GAN, being a deep learning method, is capable of modelling complicated data distributions, enabling the effective modelling of a large variety of cars. Its major weakness is that as a global method, modelling the fine details in the local region is challenging. Lazy learning works well to preserve local features by generating a local subspace with relevant data samples. We demonstrate that the combined use of GAN and lazy learning produces is able to produce high-quality results, in which different types of cars with complicated local features can be generated effectively with a single sketch. Our method outperforms existing ones using other machine learning structures such as the variational autoencoder.

A Feasibility Study on Image Inpainting for Non-cleft Lip Generation from Patients with Cleft Lip

“…non-cleft lip images) domains, which may lead to model leakage where the trained model memorizes the training images. Conditional image translation frameworks using GAN [5] or VAEs [10] may resolve the issue, but those methods mainly focus on the synthesis of new color patterns instead of geometric structures. Our investigation led us to the image inpainting framework [7] as a suitable solution, as it does not necessitate using cleft facial data for training.…”