NutriVision is an end‑to‑end framework that estimates calories, mass, fat, carbohydrates, and protein from a single RGB image and optional ingredient list. It generates depth information with DepthAnything‑V3, encodes ingredient descriptions via CLIP, and fuses visual geometry and ingredient semantics through an Ingredient‑Conditioned Frequency‑Aligned Fusion Module, an Ingredient‑Aware Mask‑based Prediction Head, and modality‑specific Internal Semantic Modeling blocks. On the Nutrition5k dataset, NutriVision achieves a mean PMAE of 13.60 ± 0.10 %, outperforming prior methods by significant margins.
arXiv:2606. 08948v1 Announce Type: cross Abstract: Comprehensive estimation of dietary micronutrients from food images could improve clinical nutrition care, but training such models requires large multimodal datasets linking diverse foods to complete nutrient profiles.
arXiv:2607. 08423v1 Announce Type: new Abstract: The rapid integration of Large Vision-Language Models (VLMs) into critical infrastructure promises to revolutionize personalized healthcare and dietary management.
The paper presents a framework that enhances single-image nutrition estimation by using multimodal large language models to inventory visible foods and verify both food identity and the suitability of proposed 2D regions for portion estimation. A whole-image review identifies gaps and triggers a single targeted recovery pass, after which recovered regions are re-verified and reconciled into a final item set. The approach, which requires no task-specific fine-tuning, improves item-level grounding, mass accuracy, energy accuracy, and item-identity precision and recall compared to a retrieval baseline.
The study introduces a multimodal framework that predicts postprandial glycemic response (PPGR) by combining image-derived macronutrient estimates with clinical variables and gut microbiome data. It jointly performs macronutrient estimation from meal images and glucose prediction, using an attention-based module to model interactions between dietary and host-specific information. Evaluated on a real-world dataset, the model outperforms existing PPGR baselines that use image-derived inputs and nearly matches methods relying on manually reported macronutrients.
arXiv:2607. 16514v1 Announce Type: cross Abstract: Image-based dietary assessment promises to replace costly, bias-prone manual recalls, but portion estimation remains a major blocker.
arXiv:2608. 03428v1 Announce Type: cross Abstract: Image based dietary assessment offers a scalable alternative to self reported food diaries, yet fine-grained food recognition remains challenging due to high intra-class variability and visually similar dishes.
The study fine‑tuned DINOv2‑base on 2,253 weighed Nutrition5k dishes to estimate food mass from a single RGB photo and compared it with the zero‑shot vision‑language model Qwen3‑VL‑32B across Nutrition5k and three external datasets. While the fine‑tuned model achieved a mean absolute error of 24.8 g on its own domain—better than Qwen—it failed to outperform Qwen on external datasets and its gram scale varied with scene coverage and differed per food type. Adding a single labeled photo of the same food reduced external error significantly, indicating that single‑image mass estimators require labeled photographs from the target setting.
arXiv:2607. 23273v1 Announce Type: cross Abstract: Computational nutrition needs precise ingredient data, but current databases are incomplete, inconsistent, and built for human reference rather than automated reasoning.
Fine-grained food image retrieval is a key task in computational gastronomy, with applications in food traceability, dietary monitoring, and smart catering systems. Although hashing-based retrieval is attractive for large-scale search due to its storage efficiency and fast Hamming-distance computation, existing methods often perform poorly in fine-grained food scenarios, where subtle local semantics and frequency-sensitive visual cues are essential.
arXiv:2609.22171v1 Announce Type: cross Abstract: Precision healthcare, particularly for conditions like hypertension and cardiovascular disease, necessitates monitoring of dietary sodium intake. How...
arXiv:2610.09726v1 Announce Type: new Abstract: Estimating remaining shelf life (RSL) from images could provide affordable decision support for perishable produce, but evaluation protocols can substa...
The study investigates how different visual representations affect the perception of food similarity in Indian cuisine. Using an expanded Khana dataset and seven pretrained models, the authors analyze image‑to‑image retrieval and image‑to‑dish neighborhoods, revealing that visual similarity can cross culinary-family boundaries and varies significantly across representations. Aggregated dish‑level similarities show some common structure, but this does not align strongly with recipe‑derived similarity, indicating that food similarity is not a fixed property but depends on representation, modality, and abstraction level.