# KitchenTwin: Semantically and Geometrically Grounded 3D Kitchen Digital Twins

Source: [KitchenTwin: Semantically and Geometrically Grounded 3D Kitchen Digital Twins](<https://www.sota2.com/research/paper/69c60f170636e5bf4afc8576>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-28T05:00:04.914Z

Authors: Quanyun Wu, Kyle Gao, Daniel Long, David A. Clausi, Jonathan Li, Yuhao Chen

Published: 2026-03-25T18:03:45.000Z

## Abstract

Embodied AI training and evaluation require object-centric digital twin environments with accurate metric geometry and semantic grounding. Recent transformer-based feedforward reconstruction methods can efficiently predict global point clouds from sparse monocular videos, yet these geometries suffer from inherent scale ambiguity and inconsistent coordinate conventions. This mismatch prevents the reliable fusion of these dimensionless point cloud predictions with locally reconstructed object meshes. We propose a novel scale-aware 3D fusion framework that registers visually grounded object meshes with transformer-predicted global point clouds to construct metrically consistent digital twins. Our method introduces a Vision-Language Model (VLM)-guided geometric anchor mechanism that resolves this fundamental coordinate mismatch by recovering an accurate real-world metric scale. To fuse these networks, we propose a geometry-aware registration pipeline that explicitly enforces physical plausibility through gravity-aligned vertical estimation, Manhattan-world structural constraints, and collision-free local refinement. Experiments on real indoor kitchen environments demonstrate improved cross-network object alignment and geometric consistency for downstream tasks, including multi-primitive fitting and metric measurement. We additionally introduce an open-source indoor digital twin dataset with metrically scaled scenes and semantically grounded and registered object-centric mesh annotations.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [3D Reconstruction Semantic Consistency on Novel real-world dataset](<https://www.sota2.com/research/sota/3d-reconstruction-semantic-consistency-on-novel-real-world-dataset.md>): 3D Reconstruction Semantic Consistency; Novel real-world dataset; Bottle 1 Score: 63.21.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.24684>)

[PDF](<https://arxiv.org/pdf/2603.24684.pdf>)
