# NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation

arXiv: https://arxiv.org/abs/2101.12378 · HTML: https://mlsanity.com/paper/2101.12378/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 44 references that are in the map.
- First posted on arXiv 29 Jan 2021.

## Builds on (most cited first, 24 of 24)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [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)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation](https://mlsanity.com/paper/1901.02970/) (2019)
- [PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation](https://mlsanity.com/paper/1812.11788/) (2018)
- [DeepIM: Deep Iterative Matching for 6D Pose Estimation](https://mlsanity.com/paper/1804.00175/) (2018)
- [3D Bounding Box Estimation Using Deep Learning and Geometry](https://mlsanity.com/paper/1612.00496/) (2016)
- [DPOD: 6D Pose Object Detector and Refiner](https://mlsanity.com/paper/1902.11020/) (2019)
- [Video Representation Learning by Dense Predictive Coding](https://mlsanity.com/paper/1909.04656/) (2019)
- [Implicit 3D Orientation Learning for 6D Object Detection from RGB Images](https://mlsanity.com/paper/1902.01275/) (2019)
- [HybridPose: 6D Object Pose Estimation under Hybrid Representations](https://mlsanity.com/paper/2001.01869/) (2020)
- [Category Level Object Pose Estimation via Neural Analysis-by-Synthesis](https://mlsanity.com/paper/2008.08145/) (2020)
- [Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views](https://mlsanity.com/paper/1505.05641/) (2015)
- [6-DoF Object Pose from Semantic Keypoints](https://mlsanity.com/paper/1703.04670/) (2017)
- [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)
- [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)
- [Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition under Occlusion](https://mlsanity.com/paper/2006.15538/) (2020)
- [Combining Compositional Models and Deep Networks For Robust Object Classification under Occlusion](https://mlsanity.com/paper/1905.11826/) (2019)
- [Click Here: Human-Localized Keypoints as Guidance for Viewpoint Estimation](https://mlsanity.com/paper/1703.09859/) (2017)

## Built on by (most cited first, 30 of 41)

- [RelPose++: Recovering 6D Poses from Sparse-view Observations](https://mlsanity.com/paper/2305.04926/) (2023)
- [RePOSE: Fast 6D Object Pose Refinement via Deep Texture Rendering](https://mlsanity.com/paper/2104.00633/) (2021)
- [Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Dataset](https://mlsanity.com/paper/2206.15436/) (2022)
- [Zero-Shot Category-Level Object Pose Estimation](https://mlsanity.com/paper/2204.03635/) (2022)
- [OOD-CV: A Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images](https://mlsanity.com/paper/2111.14341/) (2021)
- [3D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimation](https://mlsanity.com/paper/2308.10123/) (2023)
- [6DGS: 6D Pose Estimation from a Single Image and a 3D Gaussian Splatting Model](https://mlsanity.com/paper/2407.15484/) (2024)
- [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)
- [Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering](https://mlsanity.com/paper/2406.00622/) (2024)
- [FisherMatch: Semi-Supervised Rotation Regression via Entropy-based Filtering](https://mlsanity.com/paper/2203.15765/) (2022)
- [3D-Aware Visual Question Answering about Parts, Poses and Occlusions](https://mlsanity.com/paper/2310.17914/) (2023)
- [Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose](https://mlsanity.com/paper/2110.14213/) (2021)
- [OOD-CV-v2: An extended Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images](https://mlsanity.com/paper/2304.10266/) (2023)
- [NOVUM: Neural Object Volumes for Robust Object Classification](https://mlsanity.com/paper/2305.14668/) (2023)
- [Compositor: Bottom-up Clustering and Compositing for Robust Part and Object Segmentation](https://mlsanity.com/paper/2306.07404/) (2023)
- [iNeMo: Incremental Neural Mesh Models for Robust Class-Incremental Learning](https://mlsanity.com/paper/2407.09271/) (2024)
- [EigenLoRAx: Recycling Adapters to Find Principal Subspaces for Resource-Efficient Adaptation and Inference](https://mlsanity.com/paper/2502.04700/) (2025)
- [Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space](https://mlsanity.com/paper/2504.21749/) (2025)
- [You Only Look at One: Category-Level Object Representations for Pose Estimation From a Single Example](https://mlsanity.com/paper/2305.12626/) (2023)
- [Source-Free and Image-Only Unsupervised Domain Adaptation for Category Level Object Pose Estimation](https://mlsanity.com/paper/2401.10848/) (2024)
- [Reconstructing Animals and the Wild](https://mlsanity.com/paper/2411.18807/) (2024)
- [Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos](https://mlsanity.com/paper/2407.04384/) (2024)
- [Neural Textured Deformable Meshes for Robust Analysis-by-Synthesis](https://mlsanity.com/paper/2306.00118/) (2023)
- [Unified Category-Level Object Detection and Pose Estimation from RGB Images using 3D Prototypes](https://mlsanity.com/paper/2508.02157/) (2025)
- [Structured Generative Models for Scene Understanding](https://mlsanity.com/paper/2302.03531/) (2023)
- [WALT3D: Generating Realistic Training Data from Time-Lapse Imagery for Reconstructing Dynamic Objects under Occlusion](https://mlsanity.com/paper/2403.19022/) (2024)
- [SplatPose: Geometry-Aware 6-DoF Pose Estimation from Single RGB Image via 3D Gaussian Splatting](https://mlsanity.com/paper/2503.05174/) (2025)
- [Three approaches to facilitate DNN generalization to objects in out-of-distribution orientations and illuminations](https://mlsanity.com/paper/2111.00131/) (2021)
- [Self-Supervised Contrastive Representation Learning for 3D Mesh Segmentation](https://mlsanity.com/paper/2208.04278/) (2022)

## Abstract (arXiv)

3D pose estimation is a challenging but important task in computer vision. In this work, we show that standard deep learning approaches to 3D pose estimation are not robust when objects are partially occluded or viewed from a previously unseen pose. Inspired by the robustness of generative vision models to partial occlusion, we propose to integrate deep neural networks with 3D generative representations of objects into a unified neural architecture that we term NeMo. In particular, NeMo learns a generative model of neural feature activations at each vertex on a dense 3D mesh. Using differentiable rendering we estimate the 3D object pose by minimizing the reconstruction error between NeMo and the feature representation of the target image. To avoid local optima in the reconstruction loss, we train the feature extractor to maximize the distance between the individual feature representations on the mesh using contrastive learning. Our extensive experiments on PASCAL3D+, occluded-PASCAL3D+ and ObjectNet3D show that NeMo is much more robust to partial occlusion and unseen pose compared to standard deep networks, while retaining competitive performance on regular data. Interestingly, our experiments also show that NeMo performs reasonably well even when the mesh representation only crudely approximates the true object geometry with a cuboid, hence revealing that the detailed 3D geometry is not needed for accurate 3D pose estimation. The code is publicly available at https://github.com/Angtian/NeMo.