# Evaluation of Winning Solutions of 2025 Low Power Computer Vision Challenge

Source: [Evaluation of Winning Solutions of 2025 Low Power Computer Vision Challenge](<https://www.sota2.com/research/paper/69e85b977d0172140ec80f39>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-29T05:00:01.231Z

Authors: Zihao Ye, Yung-Hsiang Lu, Xiao Hu, Shuai Zhang, Taotao Jing, Xin Li, Zhen Yao, Bo Lang, Zhihao Zheng, Seungmin Oh, Hankyul Kang, Seunghun Kang, Jongbin Ryu, Kexin Chen, Yuan Qi, George K Thiruvathukal, Mooi Choo Chuah

Published: 2026-04-21T04:00:55.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on 64-category dataset leaderboard (test)](<https://www.sota2.com/research/sota/image-classification-on-64-category-dataset-leaderboard-test.md>): Image Classification; 64-category dataset leaderboard (test); Accuracy: 97.4.

- [Open-vocabulary semantic segmentation on LPCVC Track 2 leaderboard 2025 (test)](<https://www.sota2.com/research/sota/open-vocabulary-semantic-segmentation-on-lpcvc-track-2-leaderboard-2025-test.md>): Open Vocabulary Semantic Segmentation; LPCVC Track 2 leaderboard 2025 (test); mIoU: 53.2.

- [Relative Depth Estimation on LPCVC Track 3 leaderboard 2025 (test)](<https://www.sota2.com/research/sota/relative-depth-estimation-on-lpcvc-track-3-leaderboard-2025-test.md>): Relative Depth Estimation; LPCVC Track 3 leaderboard 2025 (test); F-score: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.19054>)

[PDF](<https://arxiv.org/pdf/2604.19054.pdf>)