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:2610.26538v2 Announce Type: replace-cross Abstract: Photo-based estimation of food energy could ease dietary assessment, and general-purpose multimodal large language models (LLMs) make such es...
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 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.
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: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...
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.
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.
AgriCountDINO is a parameter‑efficient, exemplar‑guided framework that jointly counts and localizes plants and their organs by conditioning frozen multiscale DINOv3 features on exemplar appearance and size, then decoding them into target points. It introduces missed‑object recovery and exemplar‑adaptive point NMS to improve detection accuracy. With only 8.4 M trainable parameters, it achieves a three‑shot MAE of 11.92 on the TPC‑268 benchmark and a zero‑shot MAE of 14.25 on unseen generic object categories in FSC‑147, outperforming previous methods without target‑domain training.
arXiv:2608. 12230v1 Announce Type: cross Abstract: Non-destructive food quality assessment has increasingly benefited from hyperspectral imaging (HSI), which captures spectral signatures linked to biochemical changes during storage.
CropCop is a closed‑set plant‑health recognition system covering 120 operational classes, built from a rigorously audited dataset of 109,107 images after removing 3,233 duplicate relationships. The model, based on a fine‑tuned DINOv3 ConvNeXt‑Tiny, achieves 98.51% accuracy and 96.87% macro‑F1 on a locked internal test, while a quantised MobileNetV4 variant reaches 98.46% accuracy and 96.23% macro‑F1 in a 22.60 MiB runtime artifact. Validation‑only post‑training quantisation and a compact ExecuTorch/XNNPACK PTE ensure high fidelity between the trained model and its deployed form, with minimal decision changes between the INT8 graph and the final artifact.
Applying South Africa's draft R3337 warning criteria to food-package photographs requires nutrition, ingredient and product-form evidence. This study presents a region-guided evidence extraction and a...