English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Dietary assessment is a key contributor to monitoring health status. Existingself-report methods are tedious and time-consuming with substantial biases anderrors. Image-based food portion estimation aims to estimate food energy valuesdirectly from food images, showing great potential for automated dietaryassessment solutions. Existing image-based methods either use a single-viewimage or incorporate multi-view images and depth information to estimate thefood energy, which either has limited performance or creates user burdens. Inthis paper, we propose an end-to-end deep learning framework for food energyestimation from a monocular image through 3D shape reconstruction. We leveragea generative model to reconstruct the voxel representation of the food objectfrom the input image to recover the missing 3D information. Our method isevaluated on a publicly available food image dataset Nutrition5k, resulting aMean Absolute Error (MAE) of 40.05 kCal and Mean Absolute Percentage Error(MAPE) of 11.47% for food energy estimation. Our method uses RGB image as theonly input at the inference stage and achieves competitive results compared tothe existing method requiring both RGB and depth information.

An End-to-end Food Portion Estimation Framework Based on Shape Reconstruction from Monocular Image