# Monocular 3D Object Position Estimation with VLMs for Human-Robot Interaction

Source: [Monocular 3D Object Position Estimation with VLMs for Human-Robot Interaction](<https://www.sota2.com/research/paper/69a66c172d603e6de3e3ce25>)

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

Data updated: 2026-03-04T05:00:12.635Z

Authors: Ari Wahl, Dorian Gawlinski, David Przewozny, Paul Chojecki, Felix Bie{\\ss}mann, Sebastian Bosse

Published: 2026-03-01T18:41:48.000Z

## Abstract

Pre-trained general-purpose Vision-Language Models (VLM) hold the potential to enhance intuitive human-machine interactions due to their rich world knowledge and 2D object detection capabilities. However, VLMs for 3D coordinates detection tasks are rare. In this work, we investigate interactive abilities of VLMs by returning 3D object positions given a monocular RGB image from a wrist-mounted camera, natural language input, and robot states. We collected and curated a heterogeneous dataset of more than 100,000 images and finetuned a VLM using QLoRA with a custom regression head. By implementing conditional routing, our model maintains its ability to process general visual queries while adding specialized 3D position estimation capabilities. Our results demonstrate robust predictive performance with a median MAE of 13 mm on the test set and a five-fold improvement over a simpler baseline without finetuning. In about 25% of the cases, predictions are within a range considered acceptable for the robot to interact with objects.

## 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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.01224>)

[PDF](<https://arxiv.org/pdf/2603.01224.pdf>)
