研究目的
To present a novel approach to photogrammetric acquisition that uses an AR HMD to predict a set of covering views and to interactively guide an operator to capture imagery from each view, ensuring sufficient coverage for high-quality 3D reconstruction.
研究成果
The AR HMD-based approach for guided 3D acquisition ensures sufficient images are acquired for reconstruction coverage and quality. A user study demonstrated that novice participants can achieve more complete reconstructions using this method compared to unguided acquisition.
研究不足
The approach relies on the AR HMD's ability to track itself relative to the environment and generate a rough geometric model. Poorly-lit scenes, moving objects, or reflective materials can disrupt tracking. The method is entirely geometry-based and does not analyze image features at runtime, assuming all parts of the scene are equally feature-rich.