NutritionVerse-Thin: An Optimized Strategy for Enabling Improved Rendering of 3D Thin Food Models
This addresses a specific issue in 3D food modeling for applications like food printing and nutrition prediction, but it is incremental as it builds on existing NeRF-based methods.
The paper tackles the problem of poor rendering of thin 3D food models, which often have holes, by proposing an optimized strategy that improves rendering quality through a thin-object-optimized differentiable reconstruction method and tailored data collection and training.
With the growth in capabilities of generative models, there has been growing interest in using photo-realistic renders of common 3D food items to improve downstream tasks such as food printing, nutrition prediction, or management of food wastage. Despite 3D modelling capabilities being more accessible than ever due to the success of NeRF based view-synthesis, such rendering methods still struggle to correctly capture thin food objects, often generating meshes with significant holes. In this study, we present an optimized strategy for enabling improved rendering of thin 3D food models, and demonstrate qualitative improvements in rendering quality. Our method generates the 3D model mesh via a proposed thin-object-optimized differentiable reconstruction method and tailors the strategy at both the data collection and training stages to better handle thin objects. While simple, we find that this technique can be employed for quick and highly consistent capturing of thin 3D objects.