TRICKY 2024 Challenge on Monocular Depth from Images of Specular and Transparent Surfaces

Pierluigi Zama Ramirez, Alex Costanzino, Fabio Tosi, Matteo Poggi, Luigi Di Stefano, Jean-Baptiste Weibel, Dominik Bauer, Doris Antensteiner, Markus Vincze, Jiaqi Li, Yachuan Huang, Junrui Zhang, Yiran Wang, Jinghong Zheng, Liao Shen, Zhiguo Cao, Ziyang Song, Zerong Wang, Ruijie Zhu, Hao Zhang et al. (14 additional authors not shown)

Abstract: This paper reports on the TRICKY 2024 challenge on Monocular Depth From images of Specular and Transparent surfaces, held in conjunction with the Transparent & Reflective objects In the wild Challenges (TRICKY) workshop at ECCV 2024. The goal of this challenge is to foster research on depth estimation and address one of the challenges that remained open in the field: the perception of non-Lambertian surfaces. The challenge focuses on the popular single-image depth estimation task, attracting more than 50 registered participants. In the final testing stage, 6 participating teams submitted their models and fact sheets.