# Discovering 3D Parts from Image Collections

arXiv: https://arxiv.org/abs/2107.13629 · HTML: https://mlsanity.com/paper/2107.13629/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 52 references that are in the map.
- First posted on arXiv 28 Jul 2021.

## Builds on (most cited first, 30 of 46)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images](https://mlsanity.com/paper/1804.01654/) (2018)
- [3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction](https://mlsanity.com/paper/1604.00449/) (2016)
- [PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding](https://mlsanity.com/paper/1812.02713/) (2018)
- [Neural 3D Mesh Renderer](https://mlsanity.com/paper/1711.07566/) (2017)
- [Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning](https://mlsanity.com/paper/1904.01786/) (2019)
- [Learning Shape Templates with Structured Implicit Functions](https://mlsanity.com/paper/1904.06447/) (2019)
- [Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer](https://mlsanity.com/paper/1908.01210/) (2019)
- [Learning a Multi-View Stereo Machine](https://mlsanity.com/paper/1708.05375/) (2017)
- [Learning Shape Abstractions by Assembling Volumetric Primitives](https://mlsanity.com/paper/1612.00404/) (2016)
- [Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency](https://mlsanity.com/paper/1704.06254/) (2017)
- [CvxNet: Learnable Convex Decomposition](https://mlsanity.com/paper/1909.05736/) (2019)
- [Self-supervised Single-view 3D Reconstruction via Semantic Consistency](https://mlsanity.com/paper/2003.06473/) (2020)
- [Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids](https://mlsanity.com/paper/1904.09970/) (2019)
- [SDM-NET: Deep Generative Network for Structured Deformable Mesh](https://mlsanity.com/paper/1908.04520/) (2019)
- [SCOPS: Self-Supervised Co-Part Segmentation](https://mlsanity.com/paper/1905.01298/) (2019)
- [Learning elementary structures for 3D shape generation and matching](https://mlsanity.com/paper/1908.04725/) (2019)
- [Shape and Viewpoint without Keypoints](https://mlsanity.com/paper/2007.10982/) (2020)

## Built on by (most cited first, 13 of 13)

- [LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discovery](https://mlsanity.com/paper/2207.03434/) (2022)
- [D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropouts](https://mlsanity.com/paper/2301.11497/) (2023)
- [PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervision](https://mlsanity.com/paper/2303.09554/) (2023)
- [Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery from Sparse Image Ensemble](https://mlsanity.com/paper/2212.11042/) (2022)
- [Share With Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency](https://mlsanity.com/paper/2204.10310/) (2022)
- [Latent Partition Implicit with Surface Codes for 3D Representation](https://mlsanity.com/paper/2207.08631/) (2022)
- [PASTA: Controllable Part-Aware Shape Generation with Autoregressive Transformers](https://mlsanity.com/paper/2407.13677/) (2024)
- [Iterative Superquadric Recomposition of 3D Objects from Multiple Views](https://mlsanity.com/paper/2309.02102/) (2023)
- [Test-time Adaptation with Slot-Centric Models](https://mlsanity.com/paper/2203.11194/) (2022)
- [Primitive-based 3D Human-Object Interaction Modelling and Programming](https://mlsanity.com/paper/2312.10714/) (2023)
- [Bent & Broken Bicycles: Leveraging synthetic data for damaged object re-identification](https://mlsanity.com/paper/2304.07883/) (2023)
- [Component Selection for Craft Assembly Tasks](https://mlsanity.com/paper/2407.14001/) (2024)
- [Taylor3DNet: Fast 3D Shape Inference With Landmark Points Based Taylor Series](https://mlsanity.com/paper/2201.06845/) (2022)

## Abstract (arXiv)

Reasoning 3D shapes from 2D images is an essential yet challenging task, especially when only single-view images are at our disposal. While an object can have a complicated shape, individual parts are usually close to geometric primitives and thus are easier to model. Furthermore, parts provide a mid-level representation that is robust to appearance variations across objects in a particular category. In this work, we tackle the problem of 3D part discovery from only 2D image collections. Instead of relying on manually annotated parts for supervision, we propose a self-supervised approach, latent part discovery (LPD). Our key insight is to learn a novel part shape prior that allows each part to fit an object shape faithfully while constrained to have simple geometry. Extensive experiments on the synthetic ShapeNet, PartNet, and real-world Pascal 3D+ datasets show that our method discovers consistent object parts and achieves favorable reconstruction accuracy compared to the existing methods with the same level of supervision.