3D object retrieval is an important yet challenging task that has drawn more and more attention in recent years. While existing approaches have made strides in addressing this issue, they are often limited to restricted settings such as image and sketch queries, which are often unfriendly interactions for common users. In order to overcome these limitations, this paper presents a novel SHREC challenge track focusing on text-based fine-grained retrieval of 3D animal models. Unlike previous SHREC challenge tracks, the proposed task is considerably more challenging, requiring participants to develop innovative approaches to tackle the problem of text-based retrieval. Despite the increased difficulty, we believe this task can potentially drive useful applications in practice and facilitate more intuitive interactions with 3D objects. Five groups participated in our competition, submitting a total of 114 runs. While the results obtained in our competition are satisfactory, we note that the challenges presented by this task are far from fully solved. As such, we provide insights into potential areas for future research and improvements. We believe we can help push the boundaries of 3D object retrieval and facilitate more user-friendly interactions via vision-language technologies. https://aichallenge.hcmus.edu.vn/textanimar
@article{arxiv.2304.06053,
title = {TextANIMAR: Text-based 3D Animal Fine-Grained Retrieval},
author = {Trung-Nghia Le and Tam V. Nguyen and Minh-Quan Le and Trong-Thuan Nguyen and Viet-Tham Huynh and Trong-Le Do and Khanh-Duy Le and Mai-Khiem Tran and Nhat Hoang-Xuan and Thang-Long Nguyen-Ho and Vinh-Tiep Nguyen and Tuong-Nghiem Diep and Khanh-Duy Ho and Xuan-Hieu Nguyen and Thien-Phuc Tran and Tuan-Anh Yang and Kim-Phat Tran and Nhu-Vinh Hoang and Minh-Quang Nguyen and E-Ro Nguyen and Minh-Khoi Nguyen-Nhat and Tuan-An To and Trung-Truc Huynh-Le and Nham-Tan Nguyen and Hoang-Chau Luong and Truong Hoai Phong and Nhat-Quynh Le-Pham and Huu-Phuc Pham and Trong-Vu Hoang and Quang-Binh Nguyen and Hai-Dang Nguyen and Akihiro Sugimoto and Minh-Triet Tran},
journal= {arXiv preprint arXiv:2304.06053},
year = {2023}
}
Comments
Accepted to Computers and Graphics (3DOR, Journal Track)