TY - UNPB
T1 - Evaluation of Winning Solutions of 2025 Low Power Computer Vision Challenge
AU - Ye, Zihao
AU - Lu, Yung-Hsiang
AU - Hu, Xiao
AU - Zhang, Shuai
AU - Jing, Taotao
AU - Li, Xin
AU - Yao, Zhen
AU - Lang, Bo
AU - Zheng, Zhihao
AU - Oh, Seungmin
AU - Kang, Hankyul
AU - Kang, Seunghun
AU - Ryu, Jongbin
AU - Chen, Kexin
AU - Qi, Yuan
AU - Thiruvathukal, George K
AU - Chuah, Mooi Choo
N1 - 11 pages, 8 figures, 4 tables
PY - 2026/4/21
Y1 - 2026/4/21
N2 - The IEEE Low-Power Computer Vision Challenge (LPCVC) aims to promote the development of efficient vision models for edge devices, balancing accuracy with constraints such as latency, memory capacity, and energy use. The 2025 challenge featured three tracks: (1) Image classification under various lighting conditions and styles, (2) Open-Vocabulary Segmentation with Text Prompt, and (3) Monocular Depth Estimation. This paper presents the design of LPCVC 2025, including its competition structure and evaluation framework, which integrates the Qualcomm AI Hub for consistent and reproducible benchmarking. The paper also introduces the top-performing solutions from each track and outlines key trends and observations. The paper concludes with suggestions for future computer vision competitions.
AB - The IEEE Low-Power Computer Vision Challenge (LPCVC) aims to promote the development of efficient vision models for edge devices, balancing accuracy with constraints such as latency, memory capacity, and energy use. The 2025 challenge featured three tracks: (1) Image classification under various lighting conditions and styles, (2) Open-Vocabulary Segmentation with Text Prompt, and (3) Monocular Depth Estimation. This paper presents the design of LPCVC 2025, including its competition structure and evaluation framework, which integrates the Qualcomm AI Hub for consistent and reproducible benchmarking. The paper also introduces the top-performing solutions from each track and outlines key trends and observations. The paper concludes with suggestions for future computer vision competitions.
KW - cs.CV
M3 - Preprint
BT - Evaluation of Winning Solutions of 2025 Low Power Computer Vision Challenge
ER -