1001 Acquisition viewpoints: efficient and versatile view-dependent modeling of real-world scenes

Modeling is a severe bottleneck for computer graphics applications. Manual modeling is time consuming and fails to capture the complexity of real-world scenes. Automated modeling based on acquiring color and depth data is a promising alternative. However, the usual approach of densely sampling the scene from a few viewpoints suffers from long acquisition times, high data redundancy, and lack of robustness, leading to incomplete models. We propose automated modeling based on sampling the scene sparsely from a dense set of viewpoints. We show that the sparse data quickly accumulates to generate models with good scene coverage. The sparse depth is acquired efficiently and robustly, which enables an interactive, operator-in-the-loop acquisition pipeline. We describe a modeling system that implements this approach. The system acquires scenes with complex geometry and complex reflective properties from thousands of viewpoints in minutes. The resulting models are compact and support photorealistic rendering at interactive rates.