# Voxel-informed Language Grounding

arXiv: https://arxiv.org/abs/2205.09710 · HTML: https://mlsanity.com/paper/2205.09710/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 36 references that are in the map.
- First posted on arXiv 19 May 2022.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](https://mlsanity.com/paper/1912.08830/) (2019)
- [Object Goal Navigation using Goal-Oriented Semantic Exploration](https://mlsanity.com/paper/2007.00643/) (2020)
- [12-in-1: Multi-Task Vision and Language Representation Learning](https://mlsanity.com/paper/1912.02315/) (2019)
- [Language2Pose: Natural Language Grounded Pose Forecasting](https://mlsanity.com/paper/1907.01108/) (2019)
- [Experience Grounds Language](https://mlsanity.com/paper/2004.10151/) (2020)
- [Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings](https://mlsanity.com/paper/1803.08495/) (2018)
- [Task-Oriented Dialogue as Dataflow Synthesis](https://mlsanity.com/paper/2009.11423/) (2020)
- [ACRONYM: A Large-Scale Grasp Dataset Based on Simulation](https://mlsanity.com/paper/2011.09584/) (2020)
- [Learning by Abstraction: The Neural State Machine](https://mlsanity.com/paper/1907.03950/) (2019)
- [A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Execution](https://mlsanity.com/paper/2107.05612/) (2021)
- [LanguageRefer: Spatial-Language Model for 3D Visual Grounding](https://mlsanity.com/paper/2107.03438/) (2021)
- [ShapeGlot: Learning Language for Shape Differentiation](https://mlsanity.com/paper/1905.02925/) (2019)
- [Language Grounding with 3D Objects](https://mlsanity.com/paper/2107.12514/) (2021)
- [PartGlot: Learning Shape Part Segmentation from Language Reference Games](https://mlsanity.com/paper/2112.06390/) (2021)
- [LegoFormer: Transformers for Block-by-Block Multi-view 3D Reconstruction](https://mlsanity.com/paper/2106.12102/) (2021)
- [Embodied Language Grounding with 3D Visual Feature Representations](https://mlsanity.com/paper/1910.01210/) (2019)
- [Language-Mediated, Object-Centric Representation Learning](https://mlsanity.com/paper/2012.15814/) (2020)

## Built on by (most cited first, 11 of 11)

- [Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation](https://mlsanity.com/paper/2209.05451/) (2022)
- [LERF: Language Embedded Radiance Fields](https://mlsanity.com/paper/2303.09553/) (2023)
- [PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models](https://mlsanity.com/paper/2212.01558/) (2022)
- [FMGS: Foundation Model Embedded 3D Gaussian Splatting for Holistic 3D Scene Understanding](https://mlsanity.com/paper/2401.01970/) (2024)
- [Scene-Driven Multimodal Knowledge Graph Construction for Embodied AI](https://mlsanity.com/paper/2311.03783/) (2023)
- [Iterative Superquadric Recomposition of 3D Objects from Multiple Views](https://mlsanity.com/paper/2309.02102/) (2023)
- [4-LEGS: 4D Language Embedded Gaussian Splatting](https://mlsanity.com/paper/2410.10719/) (2024)
- [TIGER: Text-Instructed 3D Gaussian Retrieval and Coherent Editing](https://mlsanity.com/paper/2405.14455/) (2024)
- [DetermiNet: A Large-Scale Diagnostic Dataset for Complex Visually-Grounded Referencing using Determiners](https://mlsanity.com/paper/2309.03483/) (2023)
- [Multi-Task Domain Adaptation for Language Grounding with 3D Objects](https://mlsanity.com/paper/2407.02846/) (2024)
- [Why Are You Wrong? Counterfactual Explanations for Language Grounding with 3D Objects](https://mlsanity.com/paper/2505.06030/) (2025)

## Abstract (arXiv)

Natural language applied to natural 2D images describes a fundamentally 3D world. We present the Voxel-informed Language Grounder (VLG), a language grounding model that leverages 3D geometric information in the form of voxel maps derived from the visual input using a volumetric reconstruction model. We show that VLG significantly improves grounding accuracy on SNARE, an object reference game task. At the time of writing, VLG holds the top place on the SNARE leaderboard, achieving SOTA results with a 2.0% absolute improvement.