Participants are required to submit 20 .obj mesh files corresponding to the 20 selected food items. These submissions will undergo evaluation based on the reconstruction's shape and size accuracy. It is essential for participants to review the following rules:

•	Submissions must adhere to the provided instructions. Submissions will be disqualified if they contain inappropriate content or fail to meet the submission rules.

•	Each registered participant/group can only submit the result once per day.

•	The contest is open to everyone. However, those directly involved in organizing and supporting the contest cannot enter.

•	Participants are allowed to use publicly available data and models, but they must properly attribute the source by including references in their submitted code.

•	During the final phase, the organizers will closely examine the code and 3D models submitted by the top-performing teams. Disqualification will occur for teams that do not present substantial original work, use similar code to others, or are caught cheating. Additionally, teams will be disqualified if their submitted 3D models do not accurately represent the object class’s shape. For instance, a team will face disqualification for submitting a sphere model for an object classified as a strawberry, whereas a submission featuring a model resembling a hemisphere with cone for the strawberry class will remain eligible.

•	Contestants are responsible for ensuring their submissions, including all files, data, and code, are legal and comply with regulations. The organizers are not liable for any legal issues that arise from the participants' submissions.

•	If contestants publish papers related to their competition results, they must credit the competition.

•	Contestants may use data and models available to the public, but must give credit by citing the sources in their code submissions.

•	The challenge data is not public yet, is not allowed to use for other purposes. 

Winner and Prize: The top-3 teams will be selected as winner. The winner will be invited for oral presentation at workshop and also write the technical report about the challenge. Refer to the workshop website for prize details: https://sites.google.com/view/cvpr-metafood-2024 

External sources: 
•	Participants are allowed to utilize external 3D object datasets for training purposes, such as OmniObject3D[1], NutritionVerse-3D[2], etc. The use of pre-trained models or any form of external data must be clearly disclosed in the submission.
•	Baseline 3D reconstruction methods include: 
        o	Medium/Simple: Use COLMAP for automatic reconstruction with the checkerboard available and apply Meshlab for cleaning and simplification to create a sparse 3D model, save it as an .obj file for the challenge submission.
        o	Hard: Apply existing methods such as One-2-3-4-5[3] to create multiple views from a single image, use them for 3D reconstruction, calibrate scale using a checkerboard pattern, and adjust the 3D model to real-world dimensions for accurate scene representation.


[1] Wu, Tong, et al. "Omniobject3d: Large-vocabulary 3d object dataset for realistic perception, reconstruction and generation." CVPR 2023.
[2] Tai, Chi-en Amy, et al. "Nutritionverse-3d: A 3d food model dataset for nutritional intake estimation." arXiv preprint arXiv:2304.05619, 2023
[3] Liu, Minghua, et al. "One-2-3-45: Any single image to 3d mesh in 45 seconds without per-shape optimization." Neurips, 2023.