# Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose

arXiv: https://arxiv.org/abs/2110.14213 · HTML: https://mlsanity.com/paper/2110.14213/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 60 references that are in the map.
- First posted on arXiv 27 Oct 2021.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation](https://mlsanity.com/paper/1901.02970/) (2019)
- [INeRF: Inverting Neural Radiance Fields for Pose Estimation](https://mlsanity.com/paper/2012.05877/) (2020)
- [CNN Features off-the-shelf: an Astounding Baseline for Recognition](https://mlsanity.com/paper/1403.6382/) (2014)
- [3D Bounding Box Estimation Using Deep Learning and Geometry](https://mlsanity.com/paper/1612.00496/) (2016)
- [Object Detectors Emerge in Deep Scene CNNs](https://mlsanity.com/paper/1412.6856/) (2014)
- [Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects](https://mlsanity.com/paper/1811.11553/) (2018)
- [6-DoF Object Pose from Semantic Keypoints](https://mlsanity.com/paper/1703.04670/) (2017)
- [Cross-View Image Matching for Geo-localization in Urban Environments](https://mlsanity.com/paper/1703.07815/) (2017)
- [Memory Matching Networks for One-Shot Image Recognition](https://mlsanity.com/paper/1804.08281/) (2018)
- [Learning from Synthetic Animals](https://mlsanity.com/paper/1912.08265/) (2019)
- [Learning Descriptors for Object Recognition and 3D Pose Estimation](https://mlsanity.com/paper/1502.05908/) (2015)
- [Viewpoints and Keypoints](https://mlsanity.com/paper/1411.6067/) (2014)
- [Robust Object Detection under Occlusion with Context-Aware CompositionalNets](https://mlsanity.com/paper/2005.11643/) (2020)
- [SCNet: Learning Semantic Correspondence](https://mlsanity.com/paper/1705.04043/) (2017)
- [Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusion](https://mlsanity.com/paper/2003.04490/) (2020)
- [StarMap for Category-Agnostic Keypoint and Viewpoint Estimation](https://mlsanity.com/paper/1803.09331/) (2018)
- [UnrealCV: Connecting Computer Vision to Unreal Engine](https://mlsanity.com/paper/1609.01326/) (2016)
- [NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation](https://mlsanity.com/paper/2101.12378/) (2021)
- [Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition under Occlusion](https://mlsanity.com/paper/2006.15538/) (2020)
- [Learning Local Image Descriptors with Deep Siamese and Triplet Convolutional Networks by Minimising Global Loss Functions](https://mlsanity.com/paper/1512.09272/) (2015)
- [Combining Compositional Models and Deep Networks For Robust Object Classification under Occlusion](https://mlsanity.com/paper/1905.11826/) (2019)
- [Robust Instance Segmentation through Reasoning about Multi-Object Occlusion](https://mlsanity.com/paper/2012.02107/) (2020)
- [Semi-supervised Keypoint Localization](https://mlsanity.com/paper/2101.07988/) (2021)

## Built on by (most cited first, 15 of 15)

- [Robust Category-Level 6D Pose Estimation with Coarse-to-Fine Rendering of Neural Features](https://mlsanity.com/paper/2209.05624/) (2022)
- [VoGE: A Differentiable Volume Renderer using Gaussian Ellipsoids for Analysis-by-Synthesis](https://mlsanity.com/paper/2205.15401/) (2022)
- [Generating Images with 3D Annotations Using Diffusion Models](https://mlsanity.com/paper/2306.08103/) (2023)
- [FisherMatch: Semi-Supervised Rotation Regression via Entropy-based Filtering](https://mlsanity.com/paper/2203.15765/) (2022)
- [NOVUM: Neural Object Volumes for Robust Object Classification](https://mlsanity.com/paper/2305.14668/) (2023)
- [MFOS: Model-Free & One-Shot Object Pose Estimation](https://mlsanity.com/paper/2310.01897/) (2023)
- [iNeMo: Incremental Neural Mesh Models for Robust Class-Incremental Learning](https://mlsanity.com/paper/2407.09271/) (2024)
- [Neural Textured Deformable Meshes for Robust Analysis-by-Synthesis](https://mlsanity.com/paper/2306.00118/) (2023)
- [ViewNeRF: Unsupervised Viewpoint Estimation Using Category-Level Neural Radiance Fields](https://mlsanity.com/paper/2212.00436/) (2022)
- [Robust Category-Level 3D Pose Estimation from Synthetic Data](https://mlsanity.com/paper/2305.16124/) (2023)
- [Semi-Supervised Unconstrained Head Pose Estimation in the Wild](https://mlsanity.com/paper/2404.02544/) (2024)
- [3D Shape Perception Integrates Intuitive Physics and Analysis-by-Synthesis](https://mlsanity.com/paper/2301.03711/) (2023)
- [Learning a Category-level Object Pose Estimator without Pose Annotations](https://mlsanity.com/paper/2404.05626/) (2024)
- [Piecewise Planar Hulls for Semi-Supervised Learning of 3D Shape and Pose from 2D Images](https://mlsanity.com/paper/2211.07491/) (2022)
- [DINeMo: Learning Neural Mesh Models with no 3D Annotations](https://mlsanity.com/paper/2503.20220/) (2025)

## Abstract (arXiv)

We study the problem of learning to estimate the 3D object pose from a few labelled examples and a collection of unlabelled data. Our main contribution is a learning framework, neural view synthesis and matching, that can transfer the 3D pose annotation from the labelled to unlabelled images reliably, despite unseen 3D views and nuisance variations such as the object shape, texture, illumination or scene context. In our approach, objects are represented as 3D cuboid meshes composed of feature vectors at each mesh vertex. The model is initialized from a few labelled images and is subsequently used to synthesize feature representations of unseen 3D views. The synthesized views are matched with the feature representations of unlabelled images to generate pseudo-labels of the 3D pose. The pseudo-labelled data is, in turn, used to train the feature extractor such that the features at each mesh vertex are more invariant across varying 3D views of the object. Our model is trained in an EM-type manner alternating between increasing the 3D pose invariance of the feature extractor and annotating unlabelled data through neural view synthesis and matching. We demonstrate the effectiveness of the proposed semi-supervised learning framework for 3D pose estimation on the PASCAL3D+ and KITTI datasets. We find that our approach outperforms all baselines by a wide margin, particularly in an extreme few-shot setting where only 7 annotated images are given. Remarkably, we observe that our model also achieves an exceptional robustness in out-of-distribution scenarios that involve partial occlusion.