SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2504.09623 · CVPR · 2025

Ges3ViG: Incorporating Pointing Gestures into Language-Based 3D Visual Grounding for Embodied Reference Understanding

Sanjay Sarma, Atharv Mane, Dulanga Weerakoon, Vigneshwaran Subbaraju, Sougata Sen, Archan Misra

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

3-Dimensional Embodied Reference Understanding (3D-ERU) combines a language description and an accompanying pointing gesture to identify the most relevant target object in a 3D scene. Although prior work has explored pure language-based 3D grounding, there has been limited exploration of 3D-ERU, which also incorporates human pointing gestures. To address this gap, we introduce a data augmentation framework-Imputer, and use it to curate a new benchmark dataset-ImputeRefer for 3D-ERU, by incorporating human pointing gestures into existing 3D scene datasets that only contain language instructions. We also propose Ges3ViG, a novel model for 3D-ERU that achieves ∼30% improvement in accuracy as compared to other 3D-ERU models and ∼9% compared to other purely languagebased 3D grounding models. Our code and dataset are available at https://github.com/AtharvMane/ Ges3ViG.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2504.09623")
get_code_for_paper("2504.09623")
have("2504.09623")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2504.09623.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2504.09623.svg)](https://syntology.ai/paper/2504.09623)

Connect an agent — have() is free.