# PerBite: A Curated Diagnostic Workflow for Bite-Aware Food Volume Estimation

arXiv: https://arxiv.org/abs/2606.02021 · HTML: https://mlsanity.com/paper/2606.02021/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 1 Jun 2026.

## Builds on (most cited first, 10 of 10)

- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation](https://mlsanity.com/paper/2501.12202/) (2025)
- [MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details](https://mlsanity.com/paper/2507.02546/) (2025)
- [SAM 3D: 3Dfy Anything in Images](https://mlsanity.com/paper/2511.16624/) (2025)
- [MetaFood CVPR 2024 Challenge on Physically Informed 3D Food Reconstruction: Methods and Results](https://mlsanity.com/paper/2407.09285/) (2024)
- [VolETA: One- and Few-shot Food Volume Estimation](https://mlsanity.com/paper/2407.01717/) (2024)
- [FoodMem: Near Real-time and Precise Food Video Segmentation](https://mlsanity.com/paper/2407.12121/) (2024)
- [VolTex: Food Volume Estimation using Text-Guided Segmentation and Neural Surface Reconstruction](https://mlsanity.com/paper/2506.02895/) (2025)
- [VolE: A Point-cloud Framework for Food 3D Reconstruction and Volume Estimation](https://mlsanity.com/paper/2505.10205/) (2025)
- [BenchSeg: A Large-Scale Dataset and Benchmark for Multi-View Food Video Segmentation](https://mlsanity.com/paper/2601.07581/) (2026)

## Abstract (arXiv)

Can a visually plausible food mesh be trusted to estimate the volume of consumed food? method investigates this question using selected paired before- and after-consumption states from the MetaFood CVPR 2026 Continuous 3D Reconstruction While Eating Challenge. The submitted workflow follows a curated reconstruction protocol: SAM~3 segments the food and plate regions; Hunyuan3D/SAM~3D generates a dimensionless food mesh; the plate diameter provides the metric scale; the plate geometry is removed in Blender; and the remaining mesh is hole-filled, made watertight, and integrated to estimate volume. MoGe-2 is used only as an auxiliary cue for initial dish-diameter estimation when direct plate measurement is uncertain; it is not the primary scale source for the reported challenge result. method ranks first, with an average Chamfer distance of 8.31 across 34 meshes using rigid ICP without scale correction. On 17 before- and after-pairs, it achieves 33.87% state-level volume MAPE and zero monotonicity violations, while consumed-volume MAPE remains 53.74%. The results show that surface reconstruction, metric scale, controlled mesh cleanup, watertight volume integration, and physical depletion consistency should be evaluated separately for dietary assessment. Source code and evaluation scripts will be available at hrefhttps://github.com/GCVCG/PerBite-CVPR-MetaFood-2026github.com/GCVCG/PerBite-CVPR-MetaFood-2026.