# NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimation

arXiv: https://arxiv.org/abs/2203.04802 · HTML: https://mlsanity.com/paper/2203.04802/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 70 references that are in the map.
- First posted on arXiv 9 Mar 2022.

## Builds on (most cited first, 30 of 44)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [PlenOctrees for Real-time Rendering of Neural Radiance Fields](https://mlsanity.com/paper/2103.14024/) (2021)
- [PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes](https://mlsanity.com/paper/1711.00199/) (2017)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs](https://mlsanity.com/paper/2103.13744/) (2021)
- [BARF: Bundle-Adjusting Neural Radiance Fields](https://mlsanity.com/paper/2104.06405/) (2021)
- [Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation](https://mlsanity.com/paper/1901.02970/) (2019)
- [PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment](https://mlsanity.com/paper/1908.06391/) (2019)
- [PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation](https://mlsanity.com/paper/1812.11788/) (2018)
- [INeRF: Inverting Neural Radiance Fields for Pose Estimation](https://mlsanity.com/paper/2012.05877/) (2020)
- [CosyPose: Consistent multi-view multi-object 6D pose estimation](https://mlsanity.com/paper/2008.08465/) (2020)
- [DeepIM: Deep Iterative Matching for 6D Pose Estimation](https://mlsanity.com/paper/1804.00175/) (2018)
- [BOP: Benchmark for 6D Object Pose Estimation](https://mlsanity.com/paper/1808.08319/) (2018)
- [SSD-6D: Making RGB-based 3D detection and 6D pose estimation great again](https://mlsanity.com/paper/1711.10006/) (2017)
- [A General and Adaptive Robust Loss Function](https://mlsanity.com/paper/1701.03077/) (2017)
- [Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering](https://mlsanity.com/paper/2109.01847/) (2021)
- [BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth](https://mlsanity.com/paper/1703.10896/) (2017)
- [Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation](https://mlsanity.com/paper/1908.07433/) (2019)
- [T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objects](https://mlsanity.com/paper/1701.05498/) (2017)
- [Real-Time Seamless Single Shot 6D Object Pose Prediction](https://mlsanity.com/paper/1711.08848/) (2017)
- [DPOD: 6D Pose Object Detector and Refiner](https://mlsanity.com/paper/1902.11020/) (2019)
- [Feature Weighting and Boosting for Few-Shot Segmentation](https://mlsanity.com/paper/1909.13140/) (2019)

## Built on by (most cited first, 30 of 58)

- [FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects](https://mlsanity.com/paper/2312.08344/) (2023)
- [OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models](https://mlsanity.com/paper/2301.07673/) (2023)
- [OSOP: A Multi-Stage One Shot Object Pose Estimation Framework](https://mlsanity.com/paper/2203.15533/) (2022)
- [Parallel Inversion of Neural Radiance Fields for Robust Pose Estimation](https://mlsanity.com/paper/2210.10108/) (2022)
- [Deep Learning-Based Object Pose Estimation: A Comprehensive Survey](https://mlsanity.com/paper/2405.07801/) (2024)
- [Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations](https://mlsanity.com/paper/2507.00990/) (2025)
- [MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Images](https://mlsanity.com/paper/2403.01517/) (2024)
- [BeyondPixels: A Comprehensive Review of the Evolution of Neural Radiance Fields](https://mlsanity.com/paper/2306.03000/) (2023)
- [TexPose: Neural Texture Learning for Self-Supervised 6D Object Pose Estimation](https://mlsanity.com/paper/2212.12902/) (2022)
- [Challenges for Monocular 6D Object Pose Estimation in Robotics](https://mlsanity.com/paper/2307.12172/) (2023)
- [Neural Fields in Robotics: A Survey](https://mlsanity.com/paper/2410.20220/) (2024)
- [GCE-Pose: Global Context Enhancement for Category-level Object Pose Estimation](https://mlsanity.com/paper/2502.04293/) (2025)
- [HyP-NeRF: Learning Improved NeRF Priors using a HyperNetwork](https://mlsanity.com/paper/2306.06093/) (2023)
- [Co-op: Correspondence-based Novel Object Pose Estimation](https://mlsanity.com/paper/2503.17731/) (2025)
- [SOCS: Semantically-aware Object Coordinate Space for Category-Level 6D Object Pose Estimation under Large Shape Variations](https://mlsanity.com/paper/2303.10346/) (2023)
- [JAWS: Just A Wild Shot for Cinematic Transfer in Neural Radiance Fields](https://mlsanity.com/paper/2303.15427/) (2023)
- [AI-Generated Images as Data Source: The Dawn of Synthetic Era](https://mlsanity.com/paper/2310.01830/) (2023)
- [iComMa: Inverting 3D Gaussian Splatting for Camera Pose Estimation via Comparing and Matching](https://mlsanity.com/paper/2312.09031/) (2023)
- [Open-vocabulary Mobile Manipulation in Unseen Dynamic Environments with 3D Semantic Maps](https://mlsanity.com/paper/2406.18115/) (2024)
- [PoseMatcher: One-shot 6D Object Pose Estimation by Deep Feature Matching](https://mlsanity.com/paper/2304.01382/) (2023)
- [Targeted Adversarial Attacks on Generalizable Neural Radiance Fields](https://mlsanity.com/paper/2310.03578/) (2023)
- [Zero123-6D: Zero-shot Novel View Synthesis for RGB Category-level 6D Pose Estimation](https://mlsanity.com/paper/2403.14279/) (2024)
- [Generic Objects as Pose Probes for Few-shot View Synthesis](https://mlsanity.com/paper/2408.16690/) (2024)
- [NeRF-Loc: Transformer-Based Object Localization Within Neural Radiance Fields](https://mlsanity.com/paper/2209.12068/) (2022)
- [Zero NeRF: Registration with Zero Overlap](https://mlsanity.com/paper/2211.12544/) (2022)
- [SparSplat: Fast Multi-View Reconstruction with Generalizable 2D Gaussian Splatting](https://mlsanity.com/paper/2505.02175/) (2025)
- [Look Gauss, No Pose: Novel View Synthesis using Gaussian Splatting without Accurate Pose Initialization](https://mlsanity.com/paper/2410.08743/) (2024)
- [PRISM-DP: Spatial Pose-based Observations for Diffusion-Policies via Segmentation, Mesh Generation, and Pose Tracking](https://mlsanity.com/paper/2504.20359/) (2025)
- [Factored Neural Representation for Scene Understanding](https://mlsanity.com/paper/2304.10950/) (2023)
- [Extreme Two-View Geometry From Object Poses with Diffusion Models](https://mlsanity.com/paper/2402.02800/) (2024)

## Abstract (arXiv)

Pose estimation of 3D objects in monocular images is a fundamental and long-standing problem in computer vision. Existing deep learning approaches for 6D pose estimation typically rely on the assumption of availability of 3D object models and 6D pose annotations. However, precise annotation of 6D poses in real data is intricate, time-consuming and not scalable, while synthetic data scales well but lacks realism. To avoid these problems, we present a weakly-supervised reconstruction-based pipeline, named NeRF-Pose, which needs only 2D object segmentation and known relative camera poses during training. Following the first-reconstruct-then-regress idea, we first reconstruct the objects from multiple views in the form of an implicit neural representation. Then, we train a pose regression network to predict pixel-wise 2D-3D correspondences between images and the reconstructed model. At inference, the approach only needs a single image as input. A NeRF-enabled PnP+RANSAC algorithm is used to estimate stable and accurate pose from the predicted correspondences. Experiments on LineMod and LineMod-Occlusion show that the proposed method has state-of-the-art accuracy in comparison to the best 6D pose estimation methods in spite of being trained only with weak labels. Besides, we extend the Homebrewed DB dataset with more real training images to support the weakly supervised task and achieve compelling results on this dataset. The extended dataset and code will be released soon.