Benchmark for photo-based 3D shape retrieval

With the increased use of 3D shape objects in a wide range of fields, photo-based 3D shape retrieval has recently attracted attention. Photo-based 3D shape retrieval is a newly developed search technique to retrieve 3D shape objects using a 2D photo image as the search query. We report the development of a benchmark dataset for evaluating the search performance of a photo-based 3D shape retrieval algorithm. The dataset comprises 1875 2D query images and 200 3D target objects. In addition, we conduct comparative experiments with representative feature extraction methods for photo-based 3D shape retrieval using the benchmark dataset. The experimental results suggest that the feature extraction method based on image gradient can return superior search results.