# TransNet: Category-Level Transparent Object Pose Estimation

arXiv: https://arxiv.org/abs/2208.10002 · HTML: https://mlsanity.com/paper/2208.10002/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 48 references that are in the map.
- First posted on arXiv 22 Aug 2022.

## Builds on (most cited first, 30 of 35)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [On the Variance of the Adaptive Learning Rate and Beyond](https://mlsanity.com/paper/1908.03265/) (2019)
- [Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation](https://mlsanity.com/paper/1901.02970/) (2019)
- [DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion](https://mlsanity.com/paper/1901.04780/) (2019)
- [Lookahead Optimizer: k steps forward, 1 step back](https://mlsanity.com/paper/1907.08610/) (2019)
- [Shape Prior Deformation for Categorical 6D Object Pose and Size Estimation](https://mlsanity.com/paper/2007.08454/) (2020)
- [Category-Level Articulated Object Pose Estimation](https://mlsanity.com/paper/1912.11913/) (2019)
- [ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulation](https://mlsanity.com/paper/1910.02550/) (2019)
- [Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimation](https://mlsanity.com/paper/2001.09322/) (2020)
- [FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanism](https://mlsanity.com/paper/2103.07054/) (2021)
- [Dex-NeRF: Using a Neural Radiance Field to Grasp Transparent Objects](https://mlsanity.com/paper/2110.14217/) (2021)
- [DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistency](https://mlsanity.com/paper/2103.06526/) (2021)
- [Segmenting Transparent Objects in the Wild](https://mlsanity.com/paper/2003.13948/) (2020)
- [GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Voting](https://mlsanity.com/paper/2203.07918/) (2022)
- [Gradient Centralization: A New Optimization Technique for Deep Neural Networks](https://mlsanity.com/paper/2004.01461/) (2020)
- [KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent Objects](https://mlsanity.com/paper/1912.02805/) (2019)
- [CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation](https://mlsanity.com/paper/2203.01929/) (2022)
- [RGB-D Local Implicit Function for Depth Completion of Transparent Objects](https://mlsanity.com/paper/2104.00622/) (2021)
- [ClearPose: Large-scale Transparent Object Dataset and Benchmark](https://mlsanity.com/paper/2203.03890/) (2022)
- [StereOBJ-1M: Large-scale Stereo Image Dataset for 6D Object Pose Estimation](https://mlsanity.com/paper/2109.10115/) (2021)
- [Seeing Glass: Joint Point Cloud and Depth Completion for Transparent Objects](https://mlsanity.com/paper/2110.00087/) (2021)
- [CPPF: Towards Robust Category-Level 9D Pose Estimation in the Wild](https://mlsanity.com/paper/2203.03089/) (2022)
- [TransCut: Transparent Object Segmentation from a Light-Field Image](https://mlsanity.com/paper/1511.06853/) (2015)
- [Robust 6D Object Pose Estimation by Learning RGB-D Features](https://mlsanity.com/paper/2003.00188/) (2020)
- [Uni6D: A Unified CNN Framework without Projection Breakdown for 6D Pose Estimation](https://mlsanity.com/paper/2203.14531/) (2022)
- [6D-ViT: Category-Level 6D Object Pose Estimation via Transformer-based Instance Representation Learning](https://mlsanity.com/paper/2110.04792/) (2021)

## Built on by (most cited first, 13 of 13)

- [HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimation](https://mlsanity.com/paper/2303.15743/) (2023)
- [Deep Learning-Based Object Pose Estimation: A Comprehensive Survey](https://mlsanity.com/paper/2405.07801/) (2024)
- [Challenges for Monocular 6D Object Pose Estimation in Robotics](https://mlsanity.com/paper/2307.12172/) (2023)
- [Category-level Object Detection, Pose Estimation and Reconstruction from Stereo Images](https://mlsanity.com/paper/2407.06984/) (2024)
- [Open Challenges for Monocular Single-shot 6D Object Pose Estimation](https://mlsanity.com/paper/2302.11827/) (2023)
- [TransNormal: Dense Visual Semantics for Diffusion-based Transparent Object Normal Estimation](https://mlsanity.com/paper/2602.00839/) (2026)
- [Object Pose Estimation Using Implicit Representation For Transparent Objects](https://mlsanity.com/paper/2410.13465/) (2024)
- [ReFlow6D: Refraction-Guided Transparent Object 6D Pose Estimation via Intermediate Representation Learning](https://mlsanity.com/paper/2412.20830/) (2024)
- [Enhancing Transparent Object Pose Estimation: A Fusion of GDR-Net and Edge Detection](https://mlsanity.com/paper/2502.12027/) (2025)
- [Semantic Segmentation of Transparent and Opaque Drinking Glasses with the Help of Zero-shot Learning](https://mlsanity.com/paper/2503.15004/) (2025)
- [Object Pose Estimation through Dexterous Touch](https://mlsanity.com/paper/2509.13591/) (2025)
- [DKPMV: Dense Keypoints Fusion from Multi-View RGB Frames for 6D Pose Estimation of Textureless Objects](https://mlsanity.com/paper/2510.10933/) (2025)
- [TransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimation](https://mlsanity.com/paper/2609.06665/) (2026)

## Abstract (arXiv)

Transparent objects present multiple distinct challenges to visual perception systems. First, their lack of distinguishing visual features makes transparent objects harder to detect and localize than opaque objects. Even humans find certain transparent surfaces with little specular reflection or refraction, e.g. glass doors, difficult to perceive. A second challenge is that common depth sensors typically used for opaque object perception cannot obtain accurate depth measurements on transparent objects due to their unique reflective properties. Stemming from these challenges, we observe that transparent object instances within the same category (e.g. cups) look more similar to each other than to ordinary opaque objects of that same category. Given this observation, the present paper sets out to explore the possibility of category-level transparent object pose estimation rather than instance-level pose estimation. We propose TransNet, a two-stage pipeline that learns to estimate category-level transparent object pose using localized depth completion and surface normal estimation. TransNet is evaluated in terms of pose estimation accuracy on a recent, large-scale transparent object dataset and compared to a state-of-the-art category-level pose estimation approach. Results from this comparison demonstrate that TransNet achieves improved pose estimation accuracy on transparent objects and key findings from the included ablation studies suggest future directions for performance improvements.