# S2P3: Self-Supervised Polarimetric Pose Prediction

arXiv: https://arxiv.org/abs/2312.01105 · HTML: https://mlsanity.com/paper/2312.01105/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 50 references that are in the map.
- First posted on arXiv 2 Dec 2023.

## Builds on (most cited first, 28 of 28)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Neural Scene Graphs for Dynamic Scenes](https://mlsanity.com/paper/2011.10379/) (2020)
- [Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation](https://mlsanity.com/paper/1908.07433/) (2019)
- [PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation](https://mlsanity.com/paper/1911.04231/) (2019)
- [DPOD: 6D Pose Object Detector and Refiner](https://mlsanity.com/paper/1902.11020/) (2019)
- [EPOS: Estimating 6D Pose of Objects with Symmetries](https://mlsanity.com/paper/2004.00605/) (2020)
- [FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation](https://mlsanity.com/paper/2103.02242/) (2021)
- [ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimation](https://mlsanity.com/paper/2203.09418/) (2022)
- [SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation](https://mlsanity.com/paper/2108.08367/) (2021)
- [FS6D: Few-Shot 6D Pose Estimation of Novel Objects](https://mlsanity.com/paper/2203.14628/) (2022)
- [OSOP: A Multi-Stage One Shot Object Pose Estimation Framework](https://mlsanity.com/paper/2203.15533/) (2022)
- [Self6D: Self-Supervised Monocular 6D Object Pose Estimation](https://mlsanity.com/paper/2004.06468/) (2020)
- [Shape from Polarization for Complex Scenes in the Wild](https://mlsanity.com/paper/2112.11377/) (2021)
- [PhoCaL: A Multi-Modal Dataset for Category-Level Object Pose Estimation with Photometrically Challenging Objects](https://mlsanity.com/paper/2205.08811/) (2022)
- [Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation](https://mlsanity.com/paper/2203.10339/) (2022)
- [DPODv2: Dense Correspondence-Based 6 DoF Pose Estimation](https://mlsanity.com/paper/2207.02805/) (2022)
- [Depth from a polarisation + RGB stereo pair](https://mlsanity.com/paper/1903.12061/) (2019)
- [3D Human Shape Reconstruction from a Polarization Image](https://mlsanity.com/paper/2007.09268/) (2020)
- [On the Importance of Accurate Geometry Data for Dense 3D Vision Tasks](https://mlsanity.com/paper/2303.14840/) (2023)
- [Uni6D: A Unified CNN Framework without Projection Breakdown for 6D Pose Estimation](https://mlsanity.com/paper/2203.14531/) (2022)
- [DemoGrasp: Few-Shot Learning for Robotic Grasping with Human Demonstration](https://mlsanity.com/paper/2112.02849/) (2021)
- [ES6D: A Computation Efficient and Symmetry-Aware 6D Pose Regression Framework](https://mlsanity.com/paper/2204.01080/) (2022)
- [Is my Depth Ground-Truth Good Enough? HAMMER -- Highly Accurate Multi-Modal Dataset for DEnse 3D Scene Regression](https://mlsanity.com/paper/2205.04565/) (2022)
- [Polarimetric Pose Prediction](https://mlsanity.com/paper/2112.03810/) (2021)
- [DGECN: A Depth-Guided Edge Convolutional Network for End-to-End 6D Pose Estimation](https://mlsanity.com/paper/2204.09983/) (2022)
- [Wild ToFu: Improving Range and Quality of Indirect Time-of-Flight Depth with RGB Fusion in Challenging Environments](https://mlsanity.com/paper/2112.03750/) (2021)

## Built on by (most cited first, 2 of 2)

- [GCE-Pose: Global Context Enhancement for Category-level Object Pose Estimation](https://mlsanity.com/paper/2502.04293/) (2025)
- [Zero123-6D: Zero-shot Novel View Synthesis for RGB Category-level 6D Pose Estimation](https://mlsanity.com/paper/2403.14279/) (2024)

## Abstract (arXiv)

This paper proposes the first self-supervised 6D object pose prediction from multimodal RGB+polarimetric images. The novel training paradigm comprises 1) a physical model to extract geometric information of polarized light, 2) a teacher-student knowledge distillation scheme and 3) a self-supervised loss formulation through differentiable rendering and an invertible physical constraint. Both networks leverage the physical properties of polarized light to learn robust geometric representations by encoding shape priors and polarization characteristics derived from our physical model. Geometric pseudo-labels from the teacher support the student network without the need for annotated real data. Dense appearance and geometric information of objects are obtained through a differentiable renderer with the predicted pose for self-supervised direct coupling. The student network additionally features our proposed invertible formulation of the physical shape priors that enables end-to-end self-supervised training through physical constraints of derived polarization characteristics compared against polarimetric input images. We specifically focus on photometrically challenging objects with texture-less or reflective surfaces and transparent materials for which the most prominent performance gain is reported.