mlsanityData to 7 Oct 2026

StrobeNet: Category-Level Multiview Reconstruction of Articulated Objects

arXiv 2105.08016 ↗First posted 17 May 2021cs.CV cs.CGcited by 14

Not on the map. Why?

Abstract (arXiv)

We present StrobeNet, a method for category-level 3D reconstruction of articulating objects from one or more unposed RGB images. Reconstructing general articulating object categories % has important applications, but is challenging since objects can have wide variation in shape, articulation, appearance and topology. We address this by building on the idea of category-level articulation canonicalization -- mapping observations to a canonical articulation which enables correspondence-free multiview aggregation. Our end-to-end trainable neural network estimates feature-enriched canonical 3D point clouds, articulation joints, and part segmentation from one or more unposed images of an object. These intermediate estimates are used to generate a final implicit 3D reconstruction.Our approach reconstructs objects even when they are observed in different articulations in images with large baselines, and animation of reconstructed shapes. Quantitative and qualitative evaluations on different object categories show that our method is able to achieve high reconstruction accuracy, especially as more views are added.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 52 of its 81 references that are in the map. First posted on arXiv 17 May 2021.

Builds on

52 of 81 references.

References · 52

  1. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  2. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  3. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  4. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  5. 2017End-to-end Recovery of Human Shape and Posecited by 883
  6. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  7. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  8. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  9. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  10. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 584
  11. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  12. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
38 more
  1. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  2. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 401
  3. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  4. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 332
  5. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  6. 2018DeepMVS: Learning Multi-view Stereopsiscited by 277
  7. 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
  8. 2018Video Based Reconstruction of 3D People Modelscited by 237
  9. 2019Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderercited by 221
  10. 2017Learning a Multi-View Stereo Machinecited by 194
  11. 2017Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistencycited by 177
  12. 2016Learning a Predictable and Generative Vector Representation for Objectscited by 173
  13. 2020DeepCap: Monocular Human Performance Capture Using Weak Supervisioncited by 162
  14. 2019Category-Level Articulated Object Pose Estimationcited by 158
  15. 2017Learning Efficient Point Cloud Generation for Dense 3D Object Reconstructioncited by 133
  16. 2017SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsiscited by 128
  17. 2020Self-supervised Single-view 3D Reconstruction via Semantic Consistencycited by 127
  18. 2019Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapescited by 117
  19. 2018Detailed Human Avatars from Monocular Videocited by 109
  20. 2017MarrNet: 3D Shape Reconstruction via 2.5D Sketchescited by 108
  21. 2017Hierarchical Surface Prediction for 3D Object Reconstructioncited by 89
  22. 2018Unsupervised Learning of Shape and Pose with Differentiable Point Cloudscited by 89
  23. 2020Learning Deformable Tetrahedral Meshes for 3D Reconstructioncited by 84
  24. 2020DualSDF: Semantic Shape Manipulation using a Two-Level Representationcited by 82
  25. 2016VolumeDeform: Real-time Volumetric Non-rigid Reconstructioncited by 75
  26. 2019Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priorscited by 74
  27. 2018Learning to Reconstruct Shapes from Unseen Classescited by 60
  28. 2019C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From Motioncited by 60
  29. 2014Category-Specific Object Reconstruction from a Single Imagecited by 56
  30. 2020Online Adaptation for Consistent Mesh Reconstruction in the Wildcited by 51
  31. 2020Implicit Mesh Reconstruction from Unannotated Image Collectionscited by 49
  32. 2017MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Priorcited by 36
  33. 2017Image2Mesh: A Learning Framework for Single Image 3D Reconstructioncited by 29
  34. 2017SilNet : Single- and Multi-View Reconstruction by Learning from Silhouettescited by 24
  35. 2020Pix2Surf: Learning Parametric 3D Surface Models of Objects from Imagescited by 22
  36. 2017Weakly supervised 3D Reconstruction with Adversarial Constraintcited by 13
  37. 2019Multiview Aggregation for Learning Category-Specific Shape Reconstructioncited by 12
  38. 2020Object-Centric Multi-View Aggregationcited by 6

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 4; 2023: 3; 2024: 1; 2025: 2; 2026: 3.

14 papers.

Sort:

  1. 2023Neural Kernel Surface Reconstructioncited by 102
  2. 2025ArtGS: Building Interactable Replicas of Complex Articulated Objects via Gaussian Splattingcited by 67
  3. 2021Neural Fields as Learnable Kernels for 3D Reconstructioncited by 58
  4. 2022Self-supervised Neural Articulated Shape and Appearance Modelscited by 51
  5. 2024REACTO: Reconstructing Articulated Objects from a Single Videocited by 45
  6. 2025VideoArtGS: Building Digital Twins of Articulated Objects from Monocular Videocited by 15
  7. 2022Unsupervised Kinematic Motion Detection for Part-segmented 3D Shape Collectionscited by 13
  8. 2022Canonical Fields: Self-Supervised Learning of Pose-Canonicalized Neural Fieldscited by 9
  9. 2022NARF22: Neural Articulated Radiance Fields for Configuration-Aware Renderingcited by 8
  10. 2023RoSI: Recovering 3D Shape Interiors from Few Articulation Imagescited by 6
  11. 2023Interaction-Driven Active 3D Reconstruction with Object Interiorscited by 5
  12. 2026ArtHOI: Taming Foundation Models for Monocular 4D Reconstruction of Hand-Articulated-Object Interactionscited by 3
2 more
  1. 2026ArtPro: Self-Supervised Articulated Object Reconstruction with Adaptive Integration of Mobility Proposalscited by 1
  2. 2026A Cookbook of 3D Vision: Data, Learning Paradigms, and Applicationcited by 0