# CPS++: Improving Class-level 6D Pose and Shape Estimation From Monocular Images With Self-Supervised Learning

arXiv: https://arxiv.org/abs/2003.05848 · HTML: https://mlsanity.com/paper/2003.05848/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Mar 2020.

## Built on by (most cited first, 7 of 7)

- [HouseCat6D -- A Large-Scale Multi-Modal Category Level 6D Object Perception Dataset with Household Objects in Realistic Scenarios](https://mlsanity.com/paper/2212.10428/) (2022)
- [HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimation](https://mlsanity.com/paper/2303.15743/) (2023)
- [PhoCaL: A Multi-Modal Dataset for Category-Level Object Pose Estimation with Photometrically Challenging Objects](https://mlsanity.com/paper/2205.08811/) (2022)
- [Towards Real-World Category-level Articulation Pose Estimation](https://mlsanity.com/paper/2105.03260/) (2021)
- [Optimal Pose and Shape Estimation for Category-level 3D Object Perception](https://mlsanity.com/paper/2104.08383/) (2021)
- [Optimal and Robust Category-level Perception: Object Pose and Shape Estimation from 2D and 3D Semantic Keypoints](https://mlsanity.com/paper/2206.12498/) (2022)
- [Glissando-Net: Deep sinGLe vIew category level poSe eStimation ANd 3D recOnstruction](https://mlsanity.com/paper/2501.14896/) (2025)

## Abstract (arXiv)

Contemporary monocular 6D pose estimation methods can only cope with a handful of object instances. This naturally hampers possible applications as, for instance, robots seamlessly integrated in everyday processes necessarily require the ability to work with hundreds of different objects. To tackle this problem of immanent practical relevance, we propose a novel method for class-level monocular 6D pose estimation, coupled with metric shape retrieval. Unfortunately, acquiring adequate annotations is very time-consuming and labor intensive. This is especially true for class-level 6D pose estimation, as one is required to create a highly detailed reconstruction for all objects and then annotate each object and scene using these models. To overcome this shortcoming, we additionally propose the idea of synthetic-to-real domain transfer for class-level 6D poses by means of self-supervised learning, which removes the burden of collecting numerous manual annotations. In essence, after training our proposed method fully supervised with synthetic data, we leverage recent advances in differentiable rendering to self-supervise the model with unannotated real RGB-D data to improve latter inference. We experimentally demonstrate that we can retrieve precise 6D poses and metric shapes from a single RGB image.