Real-Time Cooked Food Image Synthesis and Visual Cooking Progress Monitoring on Edge Devices
This addresses the need for efficient, user-customizable visual cooking progress monitoring on resource-constrained devices, though it is incremental in applying existing generative methods to a new domain.
The paper tackles the problem of synthesizing realistic cooked food images from raw inputs on edge devices, achieving a 30% improvement in FID scores on their dataset and 60% on public datasets.
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)