# Implicit-Scale 3D Reconstruction for Multi-Food Volume Estimation from Monocular Images

arXiv: https://arxiv.org/abs/2602.13041 · HTML: https://mlsanity.com/paper/2602.13041/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 10 references that are in the map.
- First posted on arXiv 13 Feb 2026.

## Builds on (most cited first, 6 of 6)

- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [Depth Pro: Sharp Monocular Metric Depth in Less Than a Second](https://mlsanity.com/paper/2410.02073/) (2024)
- [Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation](https://mlsanity.com/paper/2501.12202/) (2025)
- [Food Portion Estimation via 3D Object Scaling](https://mlsanity.com/paper/2404.12257/) (2024)
- [MetaFood CVPR 2024 Challenge on Physically Informed 3D Food Reconstruction: Methods and Results](https://mlsanity.com/paper/2407.09285/) (2024)
- [MFP3D: Monocular Food Portion Estimation Leveraging 3D Point Clouds](https://mlsanity.com/paper/2411.10492/) (2024)

## Built on by (most cited first, 3 of 3)

- [V-Nutri: Dish-Level Nutrition Estimation from Egocentric Cooking Videos](https://mlsanity.com/paper/2604.11913/) (2026)
- [Open-KNEAD: Knowledge-grounded Nutrition Estimation via Agentic Decomposition](https://mlsanity.com/paper/2607.12911/) (2026)
- [Geometry-Enhanced Portion Estimation for Multimodal LLMs](https://mlsanity.com/paper/2607.16514/) (2026)

## Abstract (arXiv)

We present Implicit-Scale 3D Reconstruction from Monocular Multi-Food Images, a benchmark dataset designed to advance geometry-based food portion estimation in realistic dining scenarios. Existing dietary assessment methods largely rely on single-image analysis or appearance-based inference, including recent vision-language models, which lack explicit geometric reasoning and are sensitive to scale ambiguity. This benchmark reframes food portion estimation as an implicit-scale 3D reconstruction problem under monocular observations. To reflect real-world conditions, explicit physical references and metric annotations are removed; instead, contextual objects such as plates and utensils are provided, requiring algorithms to infer scale from implicit cues and prior knowledge. The dataset emphasizes multi-food scenes with diverse object geometries, frequent occlusions, and complex spatial arrangements. The benchmark was adopted as a challenge at the MetaFood 2025 Workshop, where multiple teams proposed reconstruction-based solutions. Experimental results show that while strong vision--language baselines achieve competitive performance, geometry-based reconstruction methods provide both improved accuracy and greater robustness, with the top-performing approach achieving 0.21 MAPE in volume estimation and 5.7 L1 Chamfer Distance in geometric accuracy.