PerBite: A Curated Diagnostic Workflow for Bite-Aware Food Volume Estimation
For researchers in dietary assessment and 3D reconstruction, this work provides a curated pipeline and benchmark results, but the approach is incremental, combining existing tools (SAM, Hunyuan3D, Blender) with a focus on evaluation methodology.
The paper presents a workflow for bite-aware food volume estimation from before- and after-consumption 3D scans, achieving first place in the MetaFood CVPR 2026 challenge with an average Chamfer distance of 8.31 and 33.87% state-level volume MAPE, while highlighting the need for separate evaluation of reconstruction, scaling, and cleanup steps.
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 \href{https://github.com/GCVCG/PerBite-CVPR-MetaFood-2026}{github.com/GCVCG/PerBite-CVPR-MetaFood-2026}.