# Vision-Language Pre-training with Object Contrastive Learning for 3D Scene Understanding

arXiv: https://arxiv.org/abs/2305.10714 · HTML: https://mlsanity.com/paper/2305.10714/

## Key facts

- Cited by 25 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 43 of its 58 references that are in the map.
- First posted on arXiv 18 May 2023.

## 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 43)

- [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)
- [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)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [Deep Learning for 3D Point Clouds: A Survey](https://mlsanity.com/paper/1912.12033/) (2019)
- [PointCLIP: Point Cloud Understanding by CLIP](https://mlsanity.com/paper/2112.02413/) (2021)
- [Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression](https://mlsanity.com/paper/1911.08287/) (2019)
- [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](https://mlsanity.com/paper/1912.08830/) (2019)
- [ScanQA: 3D Question Answering for Spatial Scene Understanding](https://mlsanity.com/paper/2112.10482/) (2021)
- [Deep Modular Co-Attention Networks for Visual Question Answering](https://mlsanity.com/paper/1906.10770/) (2019)
- [Cross-Modal Contrastive Learning for Text-to-Image Generation](https://mlsanity.com/paper/2101.04702/) (2021)
- [Scan2Cap: Context-aware Dense Captioning in RGB-D Scans](https://mlsanity.com/paper/2012.02206/) (2020)

## Built on by (most cited first, 25 of 25)

- [MambaIR: A Simple Baseline for Image Restoration with State-Space Model](https://mlsanity.com/paper/2402.15648/) (2024)
- [Unifying 3D Vision-Language Understanding via Promptable Queries](https://mlsanity.com/paper/2405.11442/) (2024)
- [Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation](https://mlsanity.com/paper/2507.04047/) (2025)
- [Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders](https://mlsanity.com/paper/2312.10726/) (2023)
- [A Survey on Text-guided 3D Visual Grounding: Elements, Recent Advances, and Future Directions](https://mlsanity.com/paper/2406.05785/) (2024)
- [Bridging the Gap between 2D and 3D Visual Question Answering: A Fusion Approach for 3D VQA](https://mlsanity.com/paper/2402.15933/) (2024)
- [Object Detection with Multimodal Large Vision-Language Models: An In-depth Review](https://mlsanity.com/paper/2508.19294/) (2025)
- [3D CoCa: Contrastive Learners are 3D Captioners](https://mlsanity.com/paper/2504.09518/) (2025)
- [LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling](https://mlsanity.com/paper/2405.17149/) (2024)
- [Embodied Intelligence for 3D Understanding: A Survey on 3D Scene Question Answering](https://mlsanity.com/paper/2502.00342/) (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)
- [Advancing 3D Scene Understanding with MV-ScanQA Multi-View Reasoning Evaluation and TripAlign Pre-training Dataset](https://mlsanity.com/paper/2508.11058/) (2025)
- [LEO-VL: Efficient Scene Representation for Scalable 3D Vision-Language Learning](https://mlsanity.com/paper/2506.09935/) (2025)
- [A Review of 3D Object Detection with Vision-Language Models](https://mlsanity.com/paper/2504.18738/) (2025)
- [Uni3D-MoE: Scalable Multimodal 3D Scene Understanding via Mixture of Experts](https://mlsanity.com/paper/2505.21079/) (2025)
- [3D CoCa v2: Contrastive Learners with Test-Time Search for Generalizable Spatial Intelligence](https://mlsanity.com/paper/2601.06496/) (2026)
- [PMT-MAE: Dual-Branch Self-Supervised Learning with Distillation for Efficient Point Cloud Classification](https://mlsanity.com/paper/2409.02007/) (2024)
- [3DWG: 3D Weakly Supervised Visual Grounding via Category and Instance-Level Alignment](https://mlsanity.com/paper/2505.01809/) (2025)
- [LSVG: Language-Guided Scene Graphs with 2D-Assisted Multi-Modal Encoding for 3D Visual Grounding](https://mlsanity.com/paper/2505.04058/) (2025)
- [B2N3D: Progressive Learning from Binary to N-ary Relationships for 3D Object Grounding](https://mlsanity.com/paper/2510.10194/) (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)
- [3D-Aware VLMs with Implicit and Explicit Geometries](https://mlsanity.com/paper/2607.21595/) (2026)
- [CoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs](https://mlsanity.com/paper/2609.08345/) (2026)

## Abstract (arXiv)

In recent years, vision language pre-training frameworks have made significant progress in natural language processing and computer vision, achieving remarkable performance improvement on various downstream tasks. However, when extended to point cloud data, existing works mainly focus on building task-specific models, and fail to extract universal 3D vision-language embedding that generalize well. We carefully investigate three common tasks in semantic 3D scene understanding, and derive key insights into the development of a pre-training model. Motivated by these observations, we propose a vision-language pre-training framework 3DVLP (3D vision-language pre-training with object contrastive learning), which transfers flexibly on 3D vision-language downstream tasks. 3DVLP takes visual grounding as the proxy task and introduces Object-level IoU-guided Detection (OID) loss to obtain high-quality proposals in the scene. Moreover, we design Object-level Cross-Contrastive alignment (OCC) task and Object-level Self-Contrastive learning (OSC) task to align the objects with descriptions and distinguish different objects in the scene, respectively. Extensive experiments verify the excellent performance of 3DVLP on three 3D vision-language tasks, reflecting its superiority in semantic 3D scene understanding.