SketchANIMAR: Sketch-based 3D Animal Fine-Grained Retrieval

TL;DR

This paper introduces a new challenge track and dataset for sketch-based retrieval of 3D animal models, aiming to improve 3D object retrieval techniques and facilitate research in related applications.

Contribution

It presents a novel SHREC challenge, a new dataset ANIMAR with 711 3D animal models and 140 sketches, and provides insights into future research directions in sketch-based 3D retrieval.

Findings

Eight teams participated with 204 runs, showing promising results.

The challenge highlights the need for improved feature extraction and matching techniques.

The dataset and challenge foster further research in 3D object retrieval.

Abstract

The retrieval of 3D objects has gained significant importance in recent years due to its broad range of applications in computer vision, computer graphics, virtual reality, and augmented reality. However, the retrieval of 3D objects presents significant challenges due to the intricate nature of 3D models, which can vary in shape, size, and texture, and have numerous polygons and vertices. To this end, we introduce a novel SHREC challenge track that focuses on retrieving relevant 3D animal models from a dataset using sketch queries and expedites accessing 3D models through available sketches. Furthermore, a new dataset named ANIMAR was constructed in this study, comprising a collection of 711 unique 3D animal models and 140 corresponding sketch queries. Our contest requires participants to retrieve 3D models based on complex and detailed sketches. We receive satisfactory results from eight teams and 204 runs. Although further improvement is necessary, the proposed task has the potential to incentivize additional research in the domain of 3D object retrieval, potentially yielding benefits for a wide range of applications. We also provide insights into potential areas of future research, such as improving techniques for feature extraction and matching and creating more diverse datasets to evaluate retrieval performance. https://aichallenge.hcmus.edu.vn/sketchanimar