Real-Time Cooked Food Image Synthesis and Visual Cooking Progress Monitoring on Edge Devices

TL;DR

This paper presents an efficient edge-device capable system for realistic cooked food image synthesis and cooking progress monitoring, utilizing a new culinary dataset and a domain-specific similarity metric.

Contribution

It introduces a novel oven-based dataset, a resource-efficient generator conditioned on raw images, and a culinary-specific similarity metric for training and monitoring.

Findings

30% FID score improvement on our dataset

60% FID score improvement on public datasets

Outperforms existing baselines in realism and efficiency

Abstract

Synthesizing realistic cooked food images from raw inputs on edge devices is a challenging generative task, requiring models to capture complex changes in texture, color and structure during cooking. Existing image-to-image generation methods often produce unrealistic results or are too resource-intensive for edge deployment. We introduce the first oven-based cooking-progression dataset with chef-annotated doneness levels and propose an edge-efficient recipe and cooking state guided generator that synthesizes realistic food images conditioned on raw food image. This formulation enables user-preferred visual targets rather than fixed presets. To ensure temporal consistency and culinary plausibility, we introduce a domain-specific \textit{Culinary Image Similarity (CIS)} metric, which serves both as a training loss and a progress-monitoring signal. Our model outperforms existing baselines with significant reductions in FID scores (30\% improvement on our dataset; 60\% on public datasets)