# TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes

arXiv: https://arxiv.org/abs/2403.19589 · HTML: https://mlsanity.com/paper/2403.19589/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 63 references that are in the map.
- First posted on arXiv 28 Mar 2024.

## Builds on (most cited first, 30 of 49)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [Objaverse-XL: A Universe of 10M+ 3D Objects](https://mlsanity.com/paper/2307.05663/) (2023)
- [BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2112.11790/) (2021)
- [DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries](https://mlsanity.com/paper/2110.06922/) (2021)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection](https://mlsanity.com/paper/2206.10092/) (2022)
- [DriveLM: Driving with Graph Visual Question Answering](https://mlsanity.com/paper/2312.14150/) (2023)
- [DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models](https://mlsanity.com/paper/2402.12289/) (2024)
- [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](https://mlsanity.com/paper/1912.08830/) (2019)
- [Visual Language Maps for Robot Navigation](https://mlsanity.com/paper/2210.05714/) (2022)
- [Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation](https://mlsanity.com/paper/1811.10092/) (2018)
- [FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras](https://mlsanity.com/paper/2104.10490/) (2021)
- [Scan2Cap: Context-aware Dense Captioning in RGB-D Scans](https://mlsanity.com/paper/2012.02206/) (2020)
- [LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning](https://mlsanity.com/paper/2311.18651/) (2023)
- [3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment](https://mlsanity.com/paper/2308.04352/) (2023)
- [Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks](https://mlsanity.com/paper/1911.07883/) (2019)

## Built on by (most cited first, 30 of 40)

- [GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving](https://mlsanity.com/paper/2503.05689/) (2025)
- [MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine](https://mlsanity.com/paper/2407.08739/) (2024)
- [World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model](https://mlsanity.com/paper/2507.00603/) (2025)
- [3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer](https://mlsanity.com/paper/2501.01163/) (2025)
- [Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models](https://mlsanity.com/paper/2505.23757/) (2025)
- [Context and Geometry Aware Voxel Transformer for Semantic Scene Completion](https://mlsanity.com/paper/2405.13675/) (2024)
- [PlanAgent: A Multi-modal Large Language Agent for Closed-loop Vehicle Motion Planning](https://mlsanity.com/paper/2406.01587/) (2024)
- [Hint-AD: Holistically Aligned Interpretability in End-to-End Autonomous Driving](https://mlsanity.com/paper/2409.06702/) (2024)
- [TA-VLA: Elucidating the Design Space of Torque-aware Vision-Language-Action Models](https://mlsanity.com/paper/2509.07962/) (2025)
- [Language Driven Occupancy Prediction](https://mlsanity.com/paper/2411.16072/) (2024)
- [STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Driving](https://mlsanity.com/paper/2506.06218/) (2025)
- [DC-Scene: Data-Centric Learning for 3D Scene Understanding](https://mlsanity.com/paper/2505.15232/) (2025)
- [Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian Splatting](https://mlsanity.com/paper/2506.05280/) (2025)
- [UncAD: Towards Safe End-to-end Autonomous Driving via Online Map Uncertainty](https://mlsanity.com/paper/2504.12826/) (2025)
- [3D CoCa: Contrastive Learners are 3D Captioners](https://mlsanity.com/paper/2504.09518/) (2025)
- [NuGrounding: A Multi-View 3D Visual Grounding Framework in Autonomous Driving](https://mlsanity.com/paper/2503.22436/) (2025)
- [Extending Large Vision-Language Model for Diverse Interactive Tasks in Autonomous Driving](https://mlsanity.com/paper/2505.08725/) (2025)
- [Skip Mamba Diffusion for Monocular 3D Semantic Scene Completion](https://mlsanity.com/paper/2501.07260/) (2025)
- [Reusing Attention for One-stage Lane Topology Understanding](https://mlsanity.com/paper/2507.17617/) (2025)
- [RoboChemist: Long-Horizon and Safety-Compliant Robotic Chemical Experimentation](https://mlsanity.com/paper/2509.08820/) (2025)
- [Disentangling Instance and Scene Contexts for 3D Semantic Scene Completion](https://mlsanity.com/paper/2507.08555/) (2025)
- [BEV-LLM: Leveraging Multimodal BEV Maps for Scene Captioning in Autonomous Driving](https://mlsanity.com/paper/2507.19370/) (2025)
- [LottieGPT: Tokenizing Vector Animation for Autoregressive Generation](https://mlsanity.com/paper/2604.11792/) (2026)
- [Embedding-perturbed Exploration Preference Optimization for Flow Models](https://mlsanity.com/paper/2605.15803/) (2026)
- [PosePilot: Steering Camera Pose for Generative World Models with Self-supervised Depth](https://mlsanity.com/paper/2505.01729/) (2025)
- [LMAD: Integrated End-to-End Vision-Language Model for Explainable Autonomous Driving](https://mlsanity.com/paper/2508.12404/) (2025)
- [Instance-free Text to Point Cloud Localization with Relative Position Awareness](https://mlsanity.com/paper/2404.17845/) (2024)
- [Open 3D World in Autonomous Driving](https://mlsanity.com/paper/2408.10880/) (2024)
- [MTA: Multimodal Task Alignment for BEV Perception and Captioning](https://mlsanity.com/paper/2411.10639/) (2024)
- [3D CoCa v2: Contrastive Learners with Test-Time Search for Generalizable Spatial Intelligence](https://mlsanity.com/paper/2601.06496/) (2026)

## Abstract (arXiv)

3D dense captioning stands as a cornerstone in achieving a comprehensive understanding of 3D scenes through natural language. It has recently witnessed remarkable achievements, particularly in indoor settings. However, the exploration of 3D dense captioning in outdoor scenes is hindered by two major challenges: 1) the domain gap between indoor and outdoor scenes, such as dynamics and sparse visual inputs, makes it difficult to directly adapt existing indoor methods; 2) the lack of data with comprehensive box-caption pair annotations specifically tailored for outdoor scenes. To this end, we introduce the new task of outdoor 3D dense captioning. As input, we assume a LiDAR point cloud and a set of RGB images captured by the panoramic camera rig. The expected output is a set of object boxes with captions. To tackle this task, we propose the TOD3Cap network, which leverages the BEV representation to generate object box proposals and integrates Relation Q-Former with LLaMA-Adapter to generate rich captions for these objects. We also introduce the TOD3Cap dataset, the largest one to our knowledge for 3D dense captioning in outdoor scenes, which contains 2.3M descriptions of 64.3K outdoor objects from 850 scenes. Notably, our TOD3Cap network can effectively localize and caption 3D objects in outdoor scenes, which outperforms baseline methods by a significant margin (+9.6 CiDEr@0.5IoU). Code, data, and models are publicly available at https://github.com/jxbbb/TOD3Cap.