# Pri3D: Can 3D Priors Help 2D Representation Learning?

arXiv: https://arxiv.org/abs/2104.11225 · HTML: https://mlsanity.com/paper/2104.11225/

## Key facts

- Cited by 61 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 67 references that are in the map.
- First posted on arXiv 22 Apr 2021.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [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)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [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)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [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)
- [PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding](https://mlsanity.com/paper/2007.10985/) (2020)
- [PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation](https://mlsanity.com/paper/2004.01658/) (2020)
- [PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling](https://mlsanity.com/paper/2003.00492/) (2020)
- [3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans](https://mlsanity.com/paper/1812.07003/) (2018)

## Built on by (most cited first, 30 of 61)

- [CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion](https://mlsanity.com/paper/2210.10716/) (2022)
- [ShapeLLM: Universal 3D Object Understanding for Embodied Interaction](https://mlsanity.com/paper/2402.17766/) (2024)
- [Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data](https://mlsanity.com/paper/2203.16258/) (2022)
- [Segment Any Point Cloud Sequences by Distilling Vision Foundation Models](https://mlsanity.com/paper/2306.09347/) (2023)
- [Improving 2D Feature Representations by 3D-Aware Fine-Tuning](https://mlsanity.com/paper/2407.20229/) (2024)
- [3DRS: MLLMs Need 3D-Aware Representation Supervision for Scene Understanding](https://mlsanity.com/paper/2506.01946/) (2025)
- [Rotation-Invariant Transformer for Point Cloud Matching](https://mlsanity.com/paper/2303.08231/) (2023)
- [SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations](https://mlsanity.com/paper/2112.04680/) (2021)
- [Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2202.13589/) (2022)
- [PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection](https://mlsanity.com/paper/2303.08129/) (2023)
- [Ponder: Point Cloud Pre-training via Neural Rendering](https://mlsanity.com/paper/2301.00157/) (2022)
- [Learning Visual Representations via Language-Guided Sampling](https://mlsanity.com/paper/2302.12248/) (2023)
- [DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers](https://mlsanity.com/paper/2503.14405/) (2025)
- [Versatile Multi-Modal Pre-Training for Human-Centric Perception](https://mlsanity.com/paper/2203.13815/) (2022)
- [Multimodal Semi-Supervised Learning for 3D Objects](https://mlsanity.com/paper/2110.11601/) (2021)
- [Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis](https://mlsanity.com/paper/2210.04208/) (2022)
- [Open-Vocabulary 3D Detection via Image-level Class and Debiased Cross-modal Contrastive Learning](https://mlsanity.com/paper/2207.01987/) (2022)
- [ImLoveNet: Misaligned Image-supported Registration Network for Low-overlap Point Cloud Pairs](https://mlsanity.com/paper/2207.00826/) (2022)
- [CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion](https://mlsanity.com/paper/2402.05889/) (2024)
- [2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervision](https://mlsanity.com/paper/2310.12817/) (2023)
- [Mask3D: Pre-training 2D Vision Transformers by Learning Masked 3D Priors](https://mlsanity.com/paper/2302.14746/) (2023)
- [Joint Representation Learning for Text and 3D Point Cloud](https://mlsanity.com/paper/2301.07584/) (2023)
- [PointMBF: A Multi-scale Bidirectional Fusion Network for Unsupervised RGB-D Point Cloud Registration](https://mlsanity.com/paper/2308.04782/) (2023)
- [PCR-CG: Point Cloud Registration via Deep Explicit Color and Geometry](https://mlsanity.com/paper/2302.14418/) (2023)
- [Memory-based Adapters for Online 3D Scene Perception](https://mlsanity.com/paper/2403.06974/) (2024)
- [3D Weakly Supervised Semantic Segmentation with 2D Vision-Language Guidance](https://mlsanity.com/paper/2407.09826/) (2024)
- [PointMCD: Boosting Deep Point Cloud Encoders via Multi-view Cross-modal Distillation for 3D Shape Recognition](https://mlsanity.com/paper/2207.03128/) (2022)
- [MvDeCor: Multi-view Dense Correspondence Learning for Fine-grained 3D Segmentation](https://mlsanity.com/paper/2208.08580/) (2022)
- [Shelf-Supervised Cross-Modal Pre-Training for 3D Object Detection](https://mlsanity.com/paper/2406.10115/) (2024)
- [CMHANet: A Cross-Modal Hybrid Attention Network for Point Cloud Registration](https://mlsanity.com/paper/2603.12721/) (2026)

## Abstract (arXiv)

Recent advances in 3D perception have shown impressive progress in understanding geometric structures of 3Dshapes and even scenes. Inspired by these advances in geometric understanding, we aim to imbue image-based perception with representations learned under geometric constraints. We introduce an approach to learn view-invariant,geometry-aware representations for network pre-training, based on multi-view RGB-D data, that can then be effectively transferred to downstream 2D tasks. We propose to employ contrastive learning under both multi-view im-age constraints and image-geometry constraints to encode3D priors into learned 2D representations. This results not only in improvement over 2D-only representation learning on the image-based tasks of semantic segmentation, instance segmentation, and object detection on real-world in-door datasets, but moreover, provides significant improvement in the low data regime. We show a significant improvement of 6.0% on semantic segmentation on full data as well as 11.9% on 20% data against baselines on ScanNet.