mlsanityData to 7 Oct 2026

Seeing Glass: Joint Point Cloud and Depth Completion for Transparent Objects

arXiv 2110.00087 ↗First posted 30 Sep 2021cs.CV cs.AI cs.LGcited by 39

Not on the map. Why?

Abstract (arXiv)

The basis of many object manipulation algorithms is RGB-D input. Yet, commodity RGB-D sensors can only provide distorted depth maps for a wide range of transparent objects due light refraction and absorption. To tackle the perception challenges posed by transparent objects, we propose TranspareNet, a joint point cloud and depth completion method, with the ability to complete the depth of transparent objects in cluttered and complex scenes, even with partially filled fluid contents within the vessels. To address the shortcomings of existing transparent object data collection schemes in literature, we also propose an automated dataset creation workflow that consists of robot-controlled image collection and vision-based automatic annotation. Through this automated workflow, we created Toronto Transparent Objects Depth Dataset (TODD), which consists of nearly 15000 RGB-D images. Our experimental evaluation demonstrates that TranspareNet outperforms existing state-of-the-art depth completion methods on multiple datasets, including ClearGrasp, and that it also handles cluttered scenes when trained on TODD. Code and dataset will be released at https://www.pair.toronto.edu/TranspareNet/

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Builds on 42 of its 66 references that are in the map. First posted on arXiv 30 Sep 2021.

Builds on

42 of 66 references.

References · 42

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2020End-to-End Object Detection with Transformerscited by 7,384
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  6. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  7. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  8. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  9. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  10. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  11. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  12. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
30 more
  1. 2019From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimationcited by 379
  2. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  3. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 352
  4. 2017Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metricscited by 259
  5. 20196-DOF GraspNet: Variational Grasp Generation for Object Manipulationcited by 237
  6. 2020Non-Local Spatial Propagation Network for Depth Completioncited by 194
  7. 2016Single-Image Depth Perception in the Wildcited by 179
  8. 2020GRNet: Gridding Residual Network for Dense Point Cloud Completioncited by 174
  9. 2018Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundariescited by 144
  10. 2018High Quality Monocular Depth Estimation via Transfer Learningcited by 133
  11. 2019ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulationcited by 124
  12. 2019Learning Guided Convolutional Network for Depth Completioncited by 111
  13. 2019CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completioncited by 110
  14. 2017Grasp Pose Detection in Point Cloudscited by 107
  15. 2020S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Cloudscited by 102
  16. 2020Segmenting Transparent Objects in the Wildcited by 98
  17. 2020Guiding Monocular Depth Estimation Using Depth-Attention Volumecited by 82
  18. 2018Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimationcited by 78
  19. 2019KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent Objectscited by 75
  20. 2017Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimationcited by 70
  21. 2021RGB-D Local Implicit Function for Depth Completion of Transparent Objectscited by 64
  22. 2019S4G: Amodal Single-view Single-Shot SE(3) Grasp Detection in Cluttered Scenescited by 51
  23. 2018TOM-Net: Learning Transparent Object Matting from a Single Imagecited by 34
  24. 2018Detail Preserving Depth Estimation from a Single Image Using Attention Guided Networkscited by 31
  25. 2020A Modular Robotic Arm Control Stack for Research: Franka-Interface and FrankaPycited by 24
  26. 2019LIT: Light-field Inference of Transparency for Refractive Object Localizationcited by 14
  27. 2021Segmenting Transparent Object in the Wild with Transformercited by 13
  28. 2017Perceiving and Reasoning About Liquids Using Fully Convolutional Networkscited by 10
  29. 2019Data-Efficient Learning for Sim-to-Real Robotic Grasping using Deep Point Cloud Prediction Networkscited by 6
  30. 2018Depth Reconstruction of Translucent Objects from a Single Time-of-Flight Camera using Deep Residual Networkscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 5; 2024: 7; 2025: 13; 2026: 8.

39 papers.

Sort:

By area:

  1. 2024ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterizationcited by 60
  2. 2022TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and a Grasping Baselinecited by 55
  3. 2022Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objectscited by 49
  4. 2022ClearPose: Large-scale Transparent Object Dataset and Benchmarkcited by 46
  5. 2022StereoPose: Category-Level 6D Transparent Object Pose Estimation from Stereo Images via Back-View NOCScited by 18
  6. 2023TRansPose: Large-Scale Multispectral Dataset for Transparent Objectcited by 15
  7. 2023MVTrans: Multi-View Perception of Transparent Objectscited by 14
  8. 2022TransNet: Category-Level Transparent Object Pose Estimationcited by 13
  9. 2023FDCT: Fast Depth Completion for Transparent Objectscited by 12
  10. 2024LayeredFlow: A Real-World Benchmark for Non-Lambertian Multi-Layer Optical Flowcited by 11
  11. 2024Diffusion-Based Depth Inpainting for Transparent and Reflective Objectscited by 9
  12. 2025Monocular Depth Estimation and Segmentation for Transparent Object with Iterative Semantic and Geometric Fusioncited by 8
27 more
  1. 2025Seeing and Seeing Through the Glass: Real and Synthetic Data for Multi-Layer Depth Estimationcited by 8
  2. 2024ClearDepth: Enhanced Stereo Perception of Transparent Objects for Robotic Manipulationcited by 7
  3. 2025TransDiff: Diffusion-Based Method for Manipulating Transparent Objects Using a Single RGB-D Imagecited by 7
  4. 2022Visual-tactile Fusion for Transparent Object Grasping in Complex Backgroundscited by 5
  5. 2025Active 6D Pose Estimation for Textureless Objects using Multi-View RGB Framescited by 3
  6. 2026TransNormal: Dense Visual Semantics for Diffusion-based Transparent Object Normal Estimationcited by 2
  7. 2023TransNet: Transparent Object Manipulation Through Category-Level Pose Estimationcited by 1
  8. 2024Transparent Object Depth Completioncited by 1
  9. 2024Spiers Memorial Lecture: How to do impactful research in artificial intelligence for chemistry and materials sciencecited by 1
  10. 2024Object Pose Estimation Using Implicit Representation For Transparent Objectscited by 1
  11. 2025UASTrack: A Unified Adaptive Selection Framework with Modality-Customization in Single Object Trackingcited by 1
  12. 2025Shaken, Not Stirred: A Novel Dataset for Visual Understanding of Glasses in Human-Robot Bartending Taskscited by 1
  13. 2025StarryGazer: Leveraging Monocular Depth Estimation Models for Domain-Agnostic Single Depth Image Completioncited by 1
  14. 2026AnchorD: Metric Grounding of Monocular Depth Using Factor Graphscited by 1
  15. 2026TransBiolab: A Real-World Multi-View Dataset of Cluttered Transparent Biomedical Objectscited by 1
  16. 2023Tabletop Transparent Scene Reconstruction via Epipolar-Guided Optical Flow with Monocular Depth Completion Priorcited by 0
  17. 2025Semantic Segmentation of Transparent and Opaque Drinking Glasses with the Help of Zero-shot Learningcited by 0
  18. 2025GAA-TSO: Geometry-Aware Assisted Depth Completion for Transparent and Specular Objectscited by 0
  19. 2025HTMNet: A Hybrid Network with Transformer-Mamba Bottleneck Multimodal Fusion for Transparent and Reflective Objects Depth Completioncited by 0
  20. 2025DCIRNet: Depth Completion with Iterative Refinement for Dexterous Grasping of Transparent and Reflective Objectscited by 0
  21. 2025DidSee: Diffusion-Based Depth Completion for Material-Agnostic Robotic Perception and Manipulationcited by 0
  22. 2025Rethinking Transparent Object Grasping: Depth Completion with Monocular Depth Estimation and Instance Maskcited by 0
  23. 2026Learning Progressive Adaptation for Multi-Modal Trackingcited by 0
  24. 2026SeeGroup: Multi-Layer Depth Estimation of Transparent Surfaces via Self-Determined Groupingcited by 0
  25. 2026AISPO: Enhancing Depth Reliability for Robotic Manipulation of Non-Lambertian Objects via Affine-Invariant Shape Priorcited by 0
  26. 2026GHOST: Geometry-Guided Hallucination of Opaque Surface Texturescited by 0
  27. 2026TransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimationcited by 0