# DietDelta: A Vision-Language Approach for Dietary Assessment via Before-and-After Images

arXiv: https://arxiv.org/abs/2604.06352 · HTML: https://mlsanity.com/paper/2604.06352/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 41 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation](https://mlsanity.com/paper/2404.15506/) (2024)
- [Nutrition5k: Towards Automatic Nutritional Understanding of Generic Food](https://mlsanity.com/paper/2103.03375/) (2021)
- [Two-view 3D Reconstruction for Food Volume Estimation](https://mlsanity.com/paper/1701.03330/) (2017)
- [DeepCode: Open Agentic Coding](https://mlsanity.com/paper/2512.07921/) (2025)
- [An End-to-end Food Portion Estimation Framework Based on Shape Reconstruction from Monocular Image](https://mlsanity.com/paper/2308.01810/) (2023)
- [Food Portion Estimation via 3D Object Scaling](https://mlsanity.com/paper/2404.12257/) (2024)
- [MFP3D: Monocular Food Portion Estimation Leveraging 3D Point Clouds](https://mlsanity.com/paper/2411.10492/) (2024)
- [A Comprehensive Survey of Image-Based Food Recognition and Volume Estimation Methods for Dietary Assessment](https://mlsanity.com/paper/2106.11776/) (2021)
- [Comprehensive Evaluation of Large Multimodal Models for Nutrition Analysis: A New Benchmark Enriched with Contextual Metadata](https://mlsanity.com/paper/2507.07048/) (2025)
- [Food Portion Estimation: From Pixels to Calories](https://mlsanity.com/paper/2602.05078/) (2026)

## Abstract (arXiv)

Accurate dietary assessment is critical for precision nutrition, yet most image-based methods rely on a single pre-consumption image and provide only coarse, meal-level estimates. These approaches cannot determine what was actually consumed and often require restrictive inputs such as depth sensing, multi-view imagery, or explicit segmentation. In this paper, we propose a simple vision-language framework for food-item-level nutritional analysis using paired before-and-after eating images. Instead of relying on rigid segmentation masks, our method leverages natural language prompts to localize specific food items and estimate their weight directly from a single RGB image. We further estimate food consumption by predicting weight differences between paired images using a two-stage training strategy. We evaluate our method on three publicly available datasets and demonstrate consistent improvements over existing approaches, establishing a strong baseline for before-and-after dietary image analysis.