# 4DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understanding

arXiv: https://arxiv.org/abs/2112.02990 · HTML: https://mlsanity.com/paper/2112.02990/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 52 references that are in the map.
- First posted on arXiv 6 Dec 2021.

## Builds on (most cited first, 30 of 41)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [Frustum PointNets for 3D Object Detection from RGB-D Data](https://mlsanity.com/paper/1711.08488/) (2017)
- [Multi-view Convolutional Neural Networks for 3D Shape Recognition](https://mlsanity.com/paper/1505.00880/) (2015)
- [PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding](https://mlsanity.com/paper/2007.10985/) (2020)
- [Joint 2D-3D-Semantic Data for Indoor Scene Understanding](https://mlsanity.com/paper/1702.01105/) (2017)
- [PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation](https://mlsanity.com/paper/2004.01658/) (2020)
- [3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans](https://mlsanity.com/paper/1812.07003/) (2018)
- [Self-Supervised Pretraining of 3D Features on any Point-Cloud](https://mlsanity.com/paper/2101.02691/) (2021)
- [Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts](https://mlsanity.com/paper/2012.09165/) (2020)
- [Unsupervised Point Cloud Pre-Training via Occlusion Completion](https://mlsanity.com/paper/2010.01089/) (2020)
- [Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds](https://mlsanity.com/paper/2109.00179/) (2021)
- [OccuSeg: Occupancy-aware 3D Instance Segmentation](https://mlsanity.com/paper/2003.06537/) (2020)
- [GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud](https://mlsanity.com/paper/1812.03320/) (2018)
- [3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation](https://mlsanity.com/paper/2003.13867/) (2020)
- [Mix3D: Out-of-Context Data Augmentation for 3D Scenes](https://mlsanity.com/paper/2110.02210/) (2021)
- [H3DNet: 3D Object Detection Using Hybrid Geometric Primitives](https://mlsanity.com/paper/2006.05682/) (2020)
- [ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votes](https://mlsanity.com/paper/2001.10692/) (2020)
- [3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation](https://mlsanity.com/paper/1803.10409/) (2018)
- [Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images](https://mlsanity.com/paper/1511.02300/) (2015)

## Built on by (most cited first, 30 of 54)

- [Language-Grounded Indoor 3D Semantic Segmentation in the Wild](https://mlsanity.com/paper/2204.07761/) (2022)
- [Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining](https://mlsanity.com/paper/2302.02318/) (2023)
- [Segment Any Point Cloud Sequences by Distilling Vision Foundation Models](https://mlsanity.com/paper/2306.09347/) (2023)
- [Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?](https://mlsanity.com/paper/2212.08320/) (2022)
- [CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP](https://mlsanity.com/paper/2303.04748/) (2023)
- [UniPAD: A Universal Pre-training Paradigm for Autonomous Driving](https://mlsanity.com/paper/2310.08370/) (2023)
- [GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Clouds](https://mlsanity.com/paper/2212.03010/) (2022)
- [PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm](https://mlsanity.com/paper/2310.08586/) (2023)
- [Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2202.13589/) (2022)
- [Ponder: Point Cloud Pre-training via Neural Rendering](https://mlsanity.com/paper/2301.00157/) (2022)
- [SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation](https://mlsanity.com/paper/2311.17707/) (2023)
- [4D Contrastive Superflows are Dense 3D Representation Learners](https://mlsanity.com/paper/2407.06190/) (2024)
- [Complete-to-Partial 4D Distillation for Self-Supervised Point Cloud Sequence Representation Learning](https://mlsanity.com/paper/2212.05330/) (2022)
- [Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Models](https://mlsanity.com/paper/2305.08776/) (2023)
- [Self-supervised Learning for Pre-Training 3D Point Clouds: A Survey](https://mlsanity.com/paper/2305.04691/) (2023)
- [SGRec3D: Self-Supervised 3D Scene Graph Learning via Object-Level Scene Reconstruction](https://mlsanity.com/paper/2309.15702/) (2023)
- [A Survey of Label-Efficient Deep Learning for 3D Point Clouds](https://mlsanity.com/paper/2305.19812/) (2023)
- [Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariance](https://mlsanity.com/paper/2305.16314/) (2023)
- [Lang3DSG: Language-based contrastive pre-training for 3D Scene Graph prediction](https://mlsanity.com/paper/2310.16494/) (2023)
- [COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentation](https://mlsanity.com/paper/2210.01784/) (2022)
- [Mask3D: Pre-training 2D Vision Transformers by Learning Masked 3D Priors](https://mlsanity.com/paper/2302.14746/) (2023)
- [PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Data](https://mlsanity.com/paper/2212.04821/) (2022)
- [Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast](https://mlsanity.com/paper/2305.19623/) (2023)
- [MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling with Informative-Preserved Reconstruction and Self-Distilled Consistency](https://mlsanity.com/paper/2212.09948/) (2022)
- [LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving](https://mlsanity.com/paper/2501.04005/) (2025)
- [Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learning](https://mlsanity.com/paper/2211.06841/) (2022)
- [MIM4D: Masked Modeling with Multi-View Video for Autonomous Driving Representation Learning](https://mlsanity.com/paper/2403.08760/) (2024)
- [Shape2Scene: 3D Scene Representation Learning Through Pre-training on Shape Data](https://mlsanity.com/paper/2407.10200/) (2024)
- [SSR-2D: Semantic 3D Scene Reconstruction from 2D Images](https://mlsanity.com/paper/2302.03640/) (2023)
- [Self-supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural Calibration](https://mlsanity.com/paper/2401.12452/) (2024)

## Abstract (arXiv)

We present a new approach to instill 4D dynamic object priors into learned 3D representations by unsupervised pre-training. We observe that dynamic movement of an object through an environment provides important cues about its objectness, and thus propose to imbue learned 3D representations with such dynamic understanding, that can then be effectively transferred to improved performance in downstream 3D semantic scene understanding tasks. We propose a new data augmentation scheme leveraging synthetic 3D shapes moving in static 3D environments, and employ contrastive learning under 3D-4D constraints that encode 4D invariances into the learned 3D representations. Experiments demonstrate that our unsupervised representation learning results in improvement in downstream 3D semantic segmentation, object detection, and instance segmentation tasks, and moreover, notably improves performance in data-scarce scenarios.