mlsanityData to 7 Oct 2026

MVTrans: Multi-View Perception of Transparent Objects

arXiv 2302.11683 ↗First posted 22 Feb 2023cs.RO cs.AI cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

Transparent object perception is a crucial skill for applications such as robot manipulation in household and laboratory settings. Existing methods utilize RGB-D or stereo inputs to handle a subset of perception tasks including depth and pose estimation. However, transparent object perception remains to be an open problem. In this paper, we forgo the unreliable depth map from RGB-D sensors and extend the stereo based method. Our proposed method, MVTrans, is an end-to-end multi-view architecture with multiple perception capabilities, including depth estimation, segmentation, and pose estimation. Additionally, we establish a novel procedural photo-realistic dataset generation pipeline and create a large-scale transparent object detection dataset, Syn-TODD, which is suitable for training networks with all three modalities, RGB-D, stereo and multi-view RGB. Project Site: https://ac-rad.github.io/MVTrans/

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 30 of its 38 references that are in the map. First posted on arXiv 22 Feb 2023.

Builds on

30 of 38 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  3. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,445
  4. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  5. 2019Panoptic Feature Pyramid Networkscited by 644
  6. 2018Pyramid Stereo Matching Networkcited by 486
  7. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 352
  8. 2021A Survey of Embodied AI: From Simulators to Research Taskscited by 256
  9. 2019PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimationcited by 204
  10. 2019ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulationcited by 124
  11. 2020ACRONYM: A Large-Scale Grasp Dataset Based on Simulationcited by 115
  12. 2018Deep Depth Completion of a Single RGB-D Imagecited by 110
18 more
  1. 2020Segmenting Transparent Objects in the Wildcited by 98
  2. 2018Falling Things: A Synthetic Dataset for 3D Object Detection and Pose Estimationcited by 92
  3. 2019CoPhy: Counterfactual Learning of Physical Dynamicscited by 80
  4. 2019KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent Objectscited by 75
  5. 2021RGB-D Local Implicit Function for Depth Completion of Transparent Objectscited by 64
  6. 2020Multi-view Depth Estimation using Epipolar Spatio-Temporal Networkscited by 59
  7. 2021Enhanced Boundary Learning for Glass-like Object Segmentationcited by 48
  8. 2020MoreFusion: Multi-object Reasoning for 6D Pose Estimation from Volumetric Fusioncited by 46
  9. 2022ClearPose: Large-scale Transparent Object Dataset and Benchmarkcited by 46
  10. 2019The Best of Both Modes: Separately Leveraging RGB and Depth for Unseen Object Instance Segmentationcited by 39
  11. 2021Seeing Glass: Joint Point Cloud and Depth Completion for Transparent Objectscited by 39
  12. 2021Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real Worldcited by 30
  13. 2021SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereocited by 18
  14. 2019RGBD-GAN: Unsupervised 3D Representation Learning From Natural Image Datasets via RGBD Image Synthesiscited by 13
  15. 2021SPACE: A Simulator for Physical Interactions and Causal Learning in 3D Environmentscited by 9
  16. 2021FakeMix Augmentation Improves Transparent Object Detectioncited by 7
  17. 2021AVoE: A Synthetic 3D Dataset on Understanding Violation of Expectation for Artificial Cognitioncited by 4
  18. 2021Predicting 3D shapes, masks, and properties of materials, liquids, and objects inside transparent containers, using the TransProteus CGI datasetcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 4; 2026: 3.

14 papers.

Sort:

By area:

  1. 2024Manipulate-Anything: Automating Real-World Robots using Vision-Language Modelscited by 82
  2. 2024ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterizationcited by 60
  3. 2025RoboChemist: Long-Horizon and Safety-Compliant Robotic Chemical Experimentationcited by 9
  4. 2025Monocular Depth Estimation and Segmentation for Transparent Object with Iterative Semantic and Geometric Fusioncited by 8
  5. 2026MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentationcited by 8
  6. 2024ClearDepth: Enhanced Stereo Perception of Transparent Objects for Robotic Manipulationcited by 7
  7. 2024SAID-NeRF: Segmentation-AIDed NeRF for Depth Completion of Transparent Objectscited by 5
  8. 2024Residual-NeRF: Learning Residual NeRFs for Transparent Object Manipulationcited by 5
  9. 2024Transparent Object Depth Completioncited by 1
  10. 2025Shaken, Not Stirred: A Novel Dataset for Visual Understanding of Glasses in Human-Robot Bartending Taskscited by 1
  11. 2025EGSA-PT:Edge-Guided Spatial Attention with Progressive Training for Monocular Depth Estimation and Segmentation of Transparent Objectscited by 1
  12. 2024ReFlow6D: Refraction-Guided Transparent Object 6D Pose Estimation via Intermediate Representation Learningcited by 0
2 more
  1. 2026Transparent Fragments Contour Estimation via Visual-Tactile Fusion for Autonomous Reassemblycited by 0
  2. 2026AISPO: Enhancing Depth Reliability for Robotic Manipulation of Non-Lambertian Objects via Affine-Invariant Shape Priorcited by 0