# Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discrimination

arXiv: https://arxiv.org/abs/2008.01068 · HTML: https://mlsanity.com/paper/2008.01068/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Aug 2020.

## Built on by (most cited first, 30 of 31)

- [Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data](https://mlsanity.com/paper/2203.16258/) (2022)
- [Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding](https://mlsanity.com/paper/2304.06906/) (2023)
- [ALSO: Automotive Lidar Self-supervision by Occupancy estimation](https://mlsanity.com/paper/2212.05867/) (2022)
- [4DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understanding](https://mlsanity.com/paper/2112.02990/) (2021)
- [Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2202.13589/) (2022)
- [Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning](https://mlsanity.com/paper/2201.00785/) (2022)
- [BuildingNet: Learning to Label 3D Buildings](https://mlsanity.com/paper/2110.04955/) (2021)
- [POS-BERT: Point Cloud One-Stage BERT Pre-Training](https://mlsanity.com/paper/2204.00989/) (2022)
- [SRFeat: Learning Locally Accurate and Globally Consistent Non-Rigid Shape Correspondence](https://mlsanity.com/paper/2209.07806/) (2022)
- [3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining](https://mlsanity.com/paper/2304.06911/) (2023)
- [HVDistill: Transferring Knowledge from Images to Point Clouds via Unsupervised Hybrid-View Distillation](https://mlsanity.com/paper/2403.11817/) (2024)
- [Data Efficient 3D Learner via Knowledge Transferred from 2D Model](https://mlsanity.com/paper/2203.08479/) (2022)
- [MvDeCor: Multi-view Dense Correspondence Learning for Fine-grained 3D Segmentation](https://mlsanity.com/paper/2208.08580/) (2022)
- [Self-supervised Point Cloud Representation Learning via Separating Mixed Shapes](https://mlsanity.com/paper/2109.00452/) (2021)
- [Semi-supervised 3D shape segmentation with multilevel consistency and part substitution](https://mlsanity.com/paper/2204.08824/) (2022)
- [Self-Supervised Image Representation Learning with Geometric Set Consistency](https://mlsanity.com/paper/2203.15361/) (2022)
- [Task-Aware Sampling Layer for Point-Wise Analysis](https://mlsanity.com/paper/2107.04291/) (2021)
- [Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning](https://mlsanity.com/paper/2212.08663/) (2022)
- [Swin3D++: Effective Multi-Source Pretraining for 3D Indoor Scene Understanding](https://mlsanity.com/paper/2402.14215/) (2024)
- [PointCMC: Cross-Modal Multi-Scale Correspondences Learning for Point Cloud Understanding](https://mlsanity.com/paper/2211.12032/) (2022)
- [Upsampling Autoencoder for Self-Supervised Point Cloud Learning](https://mlsanity.com/paper/2203.10768/) (2022)
- [Multi-View Representation is What You Need for Point-Cloud Pre-Training](https://mlsanity.com/paper/2306.02558/) (2023)
- [Joint Data and Feature Augmentation for Self-Supervised Representation Learning on Point Clouds](https://mlsanity.com/paper/2211.01184/) (2022)
- [Self-supervised Learning of Rotation-invariant 3D Point Set Features using Transformer and its Self-distillation](https://mlsanity.com/paper/2308.04725/) (2023)
- [DBDNet:Partial-to-Partial Point Cloud Registration with Dual Branches Decoupling](https://mlsanity.com/paper/2310.11733/) (2023)
- [Oriented-grid Encoder for 3D Implicit Representations](https://mlsanity.com/paper/2402.06752/) (2024)
- [EPContrast: Effective Point-level Contrastive Learning for Large-scale Point Cloud Understanding](https://mlsanity.com/paper/2410.17207/) (2024)
- [Interpolation-Aware Padding for 3D Sparse Convolutional Neural Networks](https://mlsanity.com/paper/2108.06925/) (2021)
- [SHRED: 3D Shape Region Decomposition with Learned Local Operations](https://mlsanity.com/paper/2206.03480/) (2022)
- [Unsupervised Representation Learning for Diverse Deformable Shape Collections](https://mlsanity.com/paper/2310.18141/) (2023)

## Abstract (arXiv)

Although unsupervised feature learning has demonstrated its advantages to reducing the workload of data labeling and network design in many fields, existing unsupervised 3D learning methods still cannot offer a generic network for various shape analysis tasks with competitive performance to supervised methods. In this paper, we propose an unsupervised method for learning a generic and efficient shape encoding network for different shape analysis tasks. The key idea of our method is to jointly encode and learn shape and point features from unlabeled 3D point clouds. For this purpose, we adapt HR-Net to octree-based convolutional neural networks for jointly encoding shape and point features with fused multiresolution subnetworks and design a simple-yet-efficient Multiresolution Instance Discrimination (MID) loss for jointly learning the shape and point features. Our network takes a 3D point cloud as input and output both shape and point features. After training, the network is concatenated with simple task-specific back-end layers and fine-tuned for different shape analysis tasks. We evaluate the efficacy and generality of our method and validate our network and loss design with a set of shape analysis tasks, including shape classification, semantic shape segmentation, as well as shape registration tasks. With simple back-ends, our network demonstrates the best performance among all unsupervised methods and achieves competitive performance to supervised methods, especially in tasks with a small labeled dataset. For fine-grained shape segmentation, our method even surpasses existing supervised methods by a large margin.