# 3D Object Detection and Pose Estimation of Unseen Objects in Color Images with Local Surface Embeddings

arXiv: https://arxiv.org/abs/2010.04075 · HTML: https://mlsanity.com/paper/2010.04075/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Oct 2020.

## Built on by (most cited first, 22 of 22)

- [Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images](https://mlsanity.com/paper/2204.10776/) (2022)
- [GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence](https://mlsanity.com/paper/2311.14155/) (2023)
- [FoundPose: Unseen Object Pose Estimation with Foundation Features](https://mlsanity.com/paper/2311.18809/) (2023)
- [SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddings](https://mlsanity.com/paper/2111.13489/) (2021)
- [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)
- [Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions](https://mlsanity.com/paper/2203.17234/) (2022)
- [Deep Learning-Based Object Pose Estimation: A Comprehensive Survey](https://mlsanity.com/paper/2405.07801/) (2024)
- [NOPE: Novel Object Pose Estimation from a Single Image](https://mlsanity.com/paper/2303.13612/) (2023)
- [POPE: 6-DoF Promptable Pose Estimation of Any Object, in Any Scene, with One Reference](https://mlsanity.com/paper/2305.15727/) (2023)
- [One-Shot Imitation Learning: A Pose Estimation Perspective](https://mlsanity.com/paper/2310.12077/) (2023)
- [PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learning](https://mlsanity.com/paper/2105.05643/) (2021)
- [Learning to Estimate 6DoF Pose from Limited Data: A Few-Shot, Generalizable Approach using RGB Images](https://mlsanity.com/paper/2306.07598/) (2023)
- [PIZZA: A Powerful Image-only Zero-Shot Zero-CAD Approach to 6 DoF Tracking](https://mlsanity.com/paper/2209.07589/) (2022)
- [DISP6D: Disentangled Implicit Shape and Pose Learning for Scalable 6D Pose Estimation](https://mlsanity.com/paper/2107.12549/) (2021)
- [PoseMatcher: One-shot 6D Object Pose Estimation by Deep Feature Matching](https://mlsanity.com/paper/2304.01382/) (2023)
- [Scalable Unseen Objects 6-DoF Absolute Pose Estimation with Robotic Integration](https://mlsanity.com/paper/2503.05578/) (2025)
- [Efficient and Robust Training of Dense Object Nets for Multi-Object Robot Manipulation](https://mlsanity.com/paper/2206.12145/) (2022)
- [SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference](https://mlsanity.com/paper/2509.21927/) (2025)
- [Towards Symmetry-sensitive Pose Estimation: A Rotation Representation for Symmetric Object Classes](https://mlsanity.com/paper/2604.18208/) (2026)
- [LocaliseBot: Multi-view 3D object localisation with differentiable rendering for robot grasping](https://mlsanity.com/paper/2311.08438/) (2023)
- [MixRI: Mixing Features of Reference Images for Novel Object Pose Estimation](https://mlsanity.com/paper/2601.06883/) (2026)

## Abstract (arXiv)

We present an approach for detecting and estimating the 3D poses of objects in images that requires only an untextured CAD model and no training phase for new objects. Our approach combines Deep Learning and 3D geometry: It relies on an embedding of local 3D geometry to match the CAD models to the input images. For points at the surface of objects, this embedding can be computed directly from the CAD model; for image locations, we learn to predict it from the image itself. This establishes correspondences between 3D points on the CAD model and 2D locations of the input images. However, many of these correspondences are ambiguous as many points may have similar local geometries. We show that we can use Mask-RCNN in a class-agnostic way to detect the new objects without retraining and thus drastically limit the number of possible correspondences. We can then robustly estimate a 3D pose from these discriminative correspondences using a RANSAC- like algorithm. We demonstrate the performance of this approach on the T-LESS dataset, by using a small number of objects to learn the embedding and testing it on the other objects. Our experiments show that our method is on par or better than previous methods.