# 3D Vision and Language Pretraining with Large-Scale Synthetic Data

arXiv: https://arxiv.org/abs/2407.06084 · HTML: https://mlsanity.com/paper/2407.06084/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 32 of its 45 references that are in the map.
- First posted on arXiv 8 Jul 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 30 of 32)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](https://mlsanity.com/paper/1912.08830/) (2019)
- [ProcTHOR: Large-Scale Embodied AI Using Procedural Generation](https://mlsanity.com/paper/2206.06994/) (2022)
- [An Embodied Generalist Agent in 3D World](https://mlsanity.com/paper/2311.12871/) (2023)
- [ScanQA: 3D Question Answering for Spatial Scene Understanding](https://mlsanity.com/paper/2112.10482/) (2021)
- [Scan2Cap: Context-aware Dense Captioning in RGB-D Scans](https://mlsanity.com/paper/2012.02206/) (2020)
- [Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions](https://mlsanity.com/paper/2004.03967/) (2020)
- [3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment](https://mlsanity.com/paper/2308.04352/) (2023)
- [RIO: 3D Object Instance Re-Localization in Changing Indoor Environments](https://mlsanity.com/paper/1908.06109/) (2019)
- [Multi-View Transformer for 3D Visual Grounding](https://mlsanity.com/paper/2204.02174/) (2022)
- [SAT: 2D Semantics Assisted Training for 3D Visual Grounding](https://mlsanity.com/paper/2105.11450/) (2021)
- [Language Conditioned Spatial Relation Reasoning for 3D Object Grounding](https://mlsanity.com/paper/2211.09646/) (2022)
- [3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection](https://mlsanity.com/paper/2204.06272/) (2022)
- [TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Grounding](https://mlsanity.com/paper/2108.02388/) (2021)
- [X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning](https://mlsanity.com/paper/2203.00843/) (2022)
- [ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance](https://mlsanity.com/paper/2303.16894/) (2023)
- [ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation](https://mlsanity.com/paper/2009.03456/) (2020)
- [CLIP-Guided Vision-Language Pre-training for Question Answering in 3D Scenes](https://mlsanity.com/paper/2304.06061/) (2023)
- [MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes](https://mlsanity.com/paper/2203.05203/) (2022)
- [Look Around and Refer: 2D Synthetic Semantics Knowledge Distillation for 3D Visual Grounding](https://mlsanity.com/paper/2211.14241/) (2022)
- [ScanEnts3D: Exploiting Phrase-to-3D-Object Correspondences for Improved Visio-Linguistic Models in 3D Scenes](https://mlsanity.com/paper/2212.06250/) (2022)
- [Multi-CLIP: Contrastive Vision-Language Pre-training for Question Answering tasks in 3D Scenes](https://mlsanity.com/paper/2306.02329/) (2023)
- [Bridging the Gap between 2D and 3D Visual Question Answering: A Fusion Approach for 3D VQA](https://mlsanity.com/paper/2402.15933/) (2024)
- [Toward Explainable and Fine-Grained 3D Grounding through Referring Textual Phrases](https://mlsanity.com/paper/2207.01821/) (2022)
- [DODA: Data-oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/2204.01599/) (2022)

## Built on by (most cited first, 21 of 21)

- [Training-free Video Temporal Grounding using Large-scale Pre-trained Models](https://mlsanity.com/paper/2408.16219/) (2024)
- [GaussianVLM: Scene-centric 3D Vision-Language Models using Language-aligned Gaussian Splats for Embodied Reasoning and Beyond](https://mlsanity.com/paper/2507.00886/) (2025)
- [Masked Point-Entity Contrast for Open-Vocabulary 3D Scene Understanding](https://mlsanity.com/paper/2504.19500/) (2025)
- [3D Question Answering via only 2D Vision-Language Models](https://mlsanity.com/paper/2505.22143/) (2025)
- [Chorus: Multi-Teacher Pretraining for Holistic 3D Gaussian Scene Encoding](https://mlsanity.com/paper/2512.17817/) (2025)
- [Open-Vocabulary HOI Detection with Interaction-aware Prompt and Concept Calibration](https://mlsanity.com/paper/2508.03207/) (2025)
- [Advancing 3D Scene Understanding with MV-ScanQA Multi-View Reasoning Evaluation and TripAlign Pre-training Dataset](https://mlsanity.com/paper/2508.11058/) (2025)
- [ResVG: Enhancing Relation and Semantic Understanding in Multiple Instances for Visual Grounding](https://mlsanity.com/paper/2408.16314/) (2024)
- [Integrating Chain-of-Thought for Multimodal Alignment: A Study on 3D Vision-Language Learning](https://mlsanity.com/paper/2503.06232/) (2025)
- [AR-VRM: Imitating Human Motions for Visual Robot Manipulation with Analogical Reasoning](https://mlsanity.com/paper/2508.07626/) (2025)
- [OmniVTG: A Large-Scale Dataset and Training Paradigm for Open-World Video Temporal Grounding](https://mlsanity.com/paper/2604.25276/) (2026)
- [TRKT: Weakly Supervised Dynamic Scene Graph Generation with Temporal-enhanced Relation-aware Knowledge Transferring](https://mlsanity.com/paper/2508.04943/) (2025)
- [InteractMove: Text-Controlled Human-Object Interaction Generation in 3D Scenes with Movable Objects](https://mlsanity.com/paper/2509.23612/) (2025)
- [Investigating Domain Gaps for Indoor 3D Object Detection](https://mlsanity.com/paper/2508.17439/) (2025)
- [SpaCeFormer: Fast Proposal-Free Open-Vocabulary 3D Instance Segmentation](https://mlsanity.com/paper/2604.20395/) (2026)
- [Scalable Object Relation Encoding for Better 3D Spatial Reasoning in Large Language Models](https://mlsanity.com/paper/2603.24721/) (2026)
- [Prototype-Aware Multimodal Alignment for Open-Vocabulary Visual Grounding](https://mlsanity.com/paper/2509.06291/) (2025)
- [SweeperBot: Making 3D Browsing Accessible through View Analysis and Visual Question Answering](https://mlsanity.com/paper/2511.14567/) (2025)
- [Scenes as Tokens: Multi-Scale Normal Distributions Transform Tokenizer for General 3D Vision-Language Understanding](https://mlsanity.com/paper/2511.21191/) (2025)
- [Zero-Shot 3D Question Answering via Hierarchical View-to-Token Transportation](https://mlsanity.com/paper/2606.03100/) (2026)
- [Scaling Diverse Language Generation for 3D Visual Grounding](https://mlsanity.com/paper/2606.20946/) (2026)

## Abstract (arXiv)

3D Vision-Language Pre-training (3D-VLP) aims to provide a pre-train model which can bridge 3D scenes with natural language, which is an important technique for embodied intelligence. However, current 3D-VLP datasets are hindered by limited scene-level diversity and insufficient fine-grained annotations (only 1.2K scenes and 280K textual annotations in ScanScribe), primarily due to the labor-intensive of collecting and annotating 3D scenes. To overcome these obstacles, we construct SynVL3D, a comprehensive synthetic scene-text corpus with 10K indoor scenes and 1M descriptions at object, view, and room levels, which has the advantages of diverse scene data, rich textual descriptions, multi-grained 3D-text associations, and low collection cost. Utilizing the rich annotations in SynVL3D, we pre-train a simple and unified Transformer for aligning 3D and language with multi-grained pretraining tasks. Moreover, we propose a synthetic-to-real domain adaptation in downstream task fine-tuning process to address the domain shift. Through extensive experiments, we verify the effectiveness of our model design by achieving state-of-the-art performance on downstream tasks including visual grounding, dense captioning, and question answering.