IJCAl2025
/
WUJI_INF
Not watched
6
0
Fork 0
Code
Releases 0 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
Branch: master
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'master'
${ noResults }
WUJI_INF/README.md

1.9 KiB
Raw Permalink Blame History

WUJI_INF

This repository hosts the official resources for the WUJI Challenge at IJCAI 2025.

🔹 Track 1: Texture restoration based on Spikes

Track 1 focuses on high-speed, spike-based visual tasks using spike cameras. Each task is designed to explore the advantages of neuromorphic vision sensors in real-world and synthetic environments.

🧩 Task 1: Spike-guided Deblur

For details on Task 1 (Spike-guided deblur with hybrid RGB-Spike Cameras), please refer to the full dataset and submission guideline here:

🔗 Track#1-Task#1.md

Participants are expected to reconstruct both real-world and synthetic spike data. Submission should follow the prescribed folder format.

🧩 Task 2: Deocclusion

The submission format and detailed description for Task 2 (Deocclusion) please refer to guideline here:

🔗 Track#1-Task#2.md

🧩 Task 3: Color Reconstruction

For details on Task 3 (Color Reconstruction from Spike Cameras), please refer to the full dataset and submission guideline here:

🔗 Track#1-Task#3.md

Participants are expected to reconstruct both real-world and synthetic spike data. Submission should follow the prescribed folder format.

🧩 Task 4: 3D Reconstruction

For details on Task 4 (3D Reconstruction from Spike Cameras), please refer to the full dataset and submission guideline here:

🔗 Track#1-Task#4.md

Participants are expected to reconstruct both real-world and synthetic spike data. Submission should follow the prescribed folder format.

📫 Contact

For any issues, please contact the organizing team via GitHub Issues or the competition email: spikecv@outlook.com.

Please read the following content carefully:

Dear OpenI User

Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.

For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》

Agree and continue
Disagree, exit