Home

Awesome

<p align=center>Bento800🍱</p>

Figure from paper

🎑 News

🍀 Overview

Bento800 is the first manually annotated synthetic box lunch presentation dataset for novel aesthetic box lunch presentation design.

Bento800 is composited from 34 single food images in 6 categories:

<p align=center> Rice🍚(10) ; Fried Chicken🍗(5) ; Salt-grilled Salmon🐟(5) ; Tamagoyaki🧈(6) ; Croquette🍪(5) ; Fried Shrimp🍤(3) </p>

with 3 different types of food presentations:

(1) Place fried chicken on rice;

(2) Place salt-grilled salmon and tamagoyaki on rice;

(3) Place croquette and fried shrimp on rice, the fried shrimp is on the croquette.

🌱 Dataset Creation Process

Bento800🍱_Text📝

ContentToolsDetails
Resize-Paste images in Bento800 onto a transparent image.
ContentToolsDetails
Text ParaphrasingChatGPTRephrase the above sentences with the template “Rephrase: [Input] with 25 examples” and “Rephrase: [Input]"+"Please try again"×24.

Bento800🍱

ContentToolsDetails
Image CollectionGoogle ImageThese high-resolution images contain at least one complete food item.
Remove BackgroundremovebgRemove the background and unnecessary parts.
Image Compositing-Manually composite + random data augmentation.
ContentToolsDetails
Modal SegmentationDataloopManually marked visible parts and occluded parts.
Food Item Labels & Bounding Box & Ordering ListVGG Image Annotator (VIA)Manually annotated several food item attributes.

🎁 Download

ContentSizeFilesFormatDetails
Bento800🍱_Text📝 [Google Drive] [Tencent Cloud]-1600Main Folder
├  Image216MB800PNGFood images from Bento800 of size 600×600
├  Text793 KB800TXT9 descriptions for each image in Bento800
ContentSizeFilesFormatDetails
Bento800🍱v1.0 [Google Drive]-872Main Folder
├  S1_collection3.26 MB34JPG34 food images in 6 categories
├  S2_removebg2.81 MB34PNGRemove Background
├  S3_train410 MB766PNGTraining images
├  S3_val18.8 MB34PNGTesting images
├  S4_segmentation8.72 MB2JSONSemantic Segmentation
├  S5_annotation403 KB2CSVSimple text descriptions + Ordering id + Bounding Box + Food item labels

📚 Feedback

Please fill out the Bento800 Dataset Feedback Form.

I would greatly value your thoughts, suggestions, concerns or problems.

⭐ Citation

<p align=center>“We eat🍴 first with our eyes👀~ ”</p>

If you find this dataset helpful for your research, please cite it as below:


@inproceedings{zhou2022able,
  title={ABLE: Aesthetic Box Lunch Editing},
  author={Zhou, Yutong and Shimada, Nobutaka},
  booktitle={Proceedings of the 1st International Workshop on Multimedia for Cooking, Eating, and related APPlications},
  pages={53--56},
  year={2022}
}