Reconstructing vehicles from orthographic drawings using deep neural networks
This work addresses the problem of 3D vehicle reconstruction for applications in gaming and simulation, though it is incremental in its methodological approach.
This paper tackles vehicle reconstruction from orthographic drawings by proposing a system based on pixel-aligned implicit functions with an advanced sampling strategy, and introduces a novel dataset from Assetto Corsa with higher quality models than ShapeNET. The trained network generalizes well to real-world inputs, producing plausible and detailed reconstructions.
This paper explores the current state-of-the-art of object reconstruction from multiple orthographic drawings using deep neural networks. It proposes two algorithms to extract multiple views from a single image. The paper proposes a system based on pixel-aligned implicit functions (PIFu) and develops an advanced sampling strategy to generate signed distance samples. It also compares this approach to depth map regression from multiple views. Additionally, the paper uses a novel dataset for vehicle reconstruction from the racing game Assetto Corsa, which features higher quality models than the commonly used ShapeNET dataset. The trained neural network generalizes well to real-world inputs and creates plausible and detailed reconstructions.