mlsanityData to 7 Oct 2026

HM3D-ABO: A Photo-realistic Dataset for Object-centric Multi-view 3D Reconstruction

arXiv 2206.12356 ↗First posted 24 Jun 2022cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Reconstructing 3D objects is an important computer vision task that has wide application in AR/VR. Deep learning algorithm developed for this task usually relies on an unrealistic synthetic dataset, such as ShapeNet and Things3D. On the other hand, existing real-captured object-centric datasets usually do not have enough annotation to enable supervised training or reliable evaluation. In this technical report, we present a photo-realistic object-centric dataset HM3D-ABO. It is constructed by composing realistic indoor scene and realistic object. For each configuration, we provide multi-view RGB observations, a water-tight mesh model for the object, ground truth depth map and object mask. The proposed dataset could also be useful for tasks such as camera pose estimation and novel-view synthesis. The dataset generation code is released at https://github.com/zhenpeiyang/HM3D-ABO.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 39 of its 52 references that are in the map. First posted on arXiv 24 Jun 2022.

Builds on

39 of 52 references.

References · 39

  1. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  2. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  3. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  4. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  5. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  6. 2019Habitat: A Platform for Embodied AI Researchcited by 1,163
  7. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  8. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  9. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  10. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  11. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  12. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
27 more
  1. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 601
  2. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  3. 2021Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AIcited by 579
  4. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  5. 2021Habitat 2.0: Training Home Assistants to Rearrange their Habitatcited by 501
  6. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 360
  7. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 332
  8. 2019What Do Single-view 3D Reconstruction Networks Learn?cited by 259
  9. 2018Pix3D: Dataset and Methods for Single-Image 3D Shape Modelingcited by 218
  10. 2017Learning a Multi-View Stereo Machinecited by 194
  11. 2016Learning a Predictable and Generative Vector Representation for Objectscited by 173
  12. 2020Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotationscited by 155
  13. 2018Scan2CAD: Learning CAD Model Alignment in RGB-D Scanscited by 142
  14. 2021NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wildcited by 136
  15. 2020Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Imagescited by 79
  16. 2021ObjectFolder: A Dataset of Objects with Implicit Visual, Auditory, and Tactile Representationscited by 67
  17. 2016A Large Dataset of Object Scanscited by 64
  18. 2014Category-Specific Object Reconstruction from a Single Imagecited by 56
  19. 2021Extreme Rotation Estimation using Dense Correlation Volumescited by 42
  20. 2021Planar Surface Reconstruction from Sparse Viewscited by 40
  21. 2022Virtual Correspondence: Humans as a Cue for Extreme-View Geometrycited by 25
  22. 2018Extreme Relative Pose Estimation for RGB-D Scans via Scene Completioncited by 22
  23. 2020Deep Optimized Priors for 3D Shape Modeling and Reconstructioncited by 20
  24. 2016Single Image 3D Interpreter Networkcited by 19
  25. 2019Extreme Relative Pose Network under Hybrid Representationscited by 19
  26. 2022FvOR: Robust Joint Shape and Pose Optimization for Few-view Object Reconstructioncited by 19
  27. 2020On the generalization of learning-based 3D reconstructioncited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 0; 2025: 0; 2026: 1.

4 papers.

  1. 2023MVImgNet: A Large-scale Dataset of Multi-view Imagescited by 219
  2. 2023LASA: Instance Reconstruction from Real Scans using A Large-scale Aligned Shape Annotation Datasetcited by 5
  3. 2023Background Prompting for Improved Object Depthcited by 2
  4. 2026Synthetic-to-Real Domain Bridging for Single-View 3D Reconstruction of Ships for Maritime Monitoringcited by 0