# D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding

arXiv: https://arxiv.org/abs/2112.01551 · HTML: https://mlsanity.com/paper/2112.01551/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 65 references that are in the map.
- First posted on arXiv 2 Dec 2021.

## Builds on (most cited first, 30 of 53)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [Sequence Level Training with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06732/) (2015)
- [Self-critical Sequence Training for Image Captioning](https://mlsanity.com/paper/1612.00563/) (2016)
- [Long-term Recurrent Convolutional Networks for Visual Recognition and Description](https://mlsanity.com/paper/1411.4389/) (2014)
- [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](https://mlsanity.com/paper/1912.08830/) (2019)
- [MAttNet: Modular Attention Network for Referring Expression Comprehension](https://mlsanity.com/paper/1801.08186/) (2018)
- [TextCaps: a Dataset for Image Captioning with Reading Comprehension](https://mlsanity.com/paper/2003.12462/) (2020)
- [Speaker-Follower Models for Vision-and-Language Navigation](https://mlsanity.com/paper/1806.02724/) (2018)
- [An End-to-End Transformer Model for 3D Object Detection](https://mlsanity.com/paper/2109.08141/) (2021)
- [PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation](https://mlsanity.com/paper/2004.01658/) (2020)
- [Segmentation from Natural Language Expressions](https://mlsanity.com/paper/1603.06180/) (2016)

## Built on by (most cited first, 30 of 52)

- [Text2Tex: Text-driven Texture Synthesis via Diffusion Models](https://mlsanity.com/paper/2303.11396/) (2023)
- [Multi3DRefer: Grounding Text Description to Multiple 3D Objects](https://mlsanity.com/paper/2309.05251/) (2023)
- [Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors](https://mlsanity.com/paper/2505.24625/) (2025)
- [3DRS: MLLMs Need 3D-Aware Representation Supervision for Scene Understanding](https://mlsanity.com/paper/2506.01946/) (2025)
- [VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding](https://mlsanity.com/paper/2410.13860/) (2024)
- [Federated Learning via Decentralized Dataset Distillation in Resource-Constrained Edge Environments](https://mlsanity.com/paper/2208.11311/) (2022)
- [3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding](https://mlsanity.com/paper/2507.23478/) (2025)
- [SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors](https://mlsanity.com/paper/2311.17261/) (2023)
- [When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models](https://mlsanity.com/paper/2405.10255/) (2024)
- [3D Aware Region Prompted Vision Language Model](https://mlsanity.com/paper/2509.13317/) (2025)
- [M3DBench: Let's Instruct Large Models with Multi-modal 3D Prompts](https://mlsanity.com/paper/2312.10763/) (2023)
- [Towards Explainable 3D Grounded Visual Question Answering: A New Benchmark and Strong Baseline](https://mlsanity.com/paper/2209.12028/) (2022)
- [A Survey on Text-guided 3D Visual Grounding: Elements, Recent Advances, and Future Directions](https://mlsanity.com/paper/2406.05785/) (2024)
- [RefMask3D: Language-Guided Transformer for 3D Referring Segmentation](https://mlsanity.com/paper/2407.18244/) (2024)
- [Mono3DVG: 3D Visual Grounding in Monocular Images](https://mlsanity.com/paper/2312.08022/) (2023)
- [Collaborative Novel Object Discovery and Box-Guided Cross-Modal Alignment for Open-Vocabulary 3D Object Detection](https://mlsanity.com/paper/2406.00830/) (2024)
- [DC-Scene: Data-Centric Learning for 3D Scene Understanding](https://mlsanity.com/paper/2505.15232/) (2025)
- [Recent Advances in Multi-modal 3D Intelligence: A Comprehensive Survey and Evaluation](https://mlsanity.com/paper/2310.15676/) (2023)
- [SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding](https://mlsanity.com/paper/2506.21924/) (2025)
- [Transcrib3D: 3D Referring Expression Resolution through Large Language Models](https://mlsanity.com/paper/2404.19221/) (2024)
- [Task-oriented Sequential Grounding and Navigation in 3D Scenes](https://mlsanity.com/paper/2408.04034/) (2024)
- [PerLA: Perceptive 3D Language Assistant](https://mlsanity.com/paper/2411.19774/) (2024)
- [Ges3ViG: Incorporating Pointing Gestures into Language-Based 3D Visual Grounding for Embodied Reference Understanding](https://mlsanity.com/paper/2504.09623/) (2025)
- [Map2Thought: Explicit 3D Spatial Reasoning via Metric Cognitive Maps](https://mlsanity.com/paper/2601.11442/) (2026)
- [MoE3D: Mixture of Experts meets Multi-Modal 3D Understanding](https://mlsanity.com/paper/2511.22103/) (2025)
- [Bi-directional Contextual Attention for 3D Dense Captioning](https://mlsanity.com/paper/2408.06662/) (2024)
- [SeCG: Semantic-Enhanced 3D Visual Grounding via Cross-modal Graph Attention](https://mlsanity.com/paper/2403.08182/) (2024)
- [See It All: Contextualized Late Aggregation for 3D Dense Captioning](https://mlsanity.com/paper/2408.07648/) (2024)
- [Multi-Object 3D Grounding with Dynamic Modules and Language-Informed Spatial Attention](https://mlsanity.com/paper/2410.22306/) (2024)
- [ExCap3D: Expressive 3D Scene Understanding via Object Captioning with Varying Detail](https://mlsanity.com/paper/2503.17044/) (2025)

## Abstract (arXiv)

Recent studies on dense captioning and visual grounding in 3D have achieved impressive results. Despite developments in both areas, the limited amount of available 3D vision-language data causes overfitting issues for 3D visual grounding and 3D dense captioning methods. Also, how to discriminatively describe objects in complex 3D environments is not fully studied yet. To address these challenges, we present D3Net, an end-to-end neural speaker-listener architecture that can detect, describe and discriminate. Our D3Net unifies dense captioning and visual grounding in 3D in a self-critical manner. This self-critical property of D3Net also introduces discriminability during object caption generation and enables semi-supervised training on ScanNet data with partially annotated descriptions. Our method outperforms SOTA methods in both tasks on the ScanRefer dataset, surpassing the SOTA 3D dense captioning method by a significant margin.