mlsanityData to 14 Oct 2026

Learning 3D Object Categories by Looking Around Them

arXiv 1705.03951 ↗First posted 10 May 2017cs.CVcited by 26

Not on the map. Why?

Abstract (arXiv)

Traditional approaches for learning 3D object categories use either synthetic data or manual supervision. In this paper, we propose a method which does not require manual annotations and is instead cued by observing objects from a moving vantage point. Our system builds on two innovations: a Siamese viewpoint factorization network that robustly aligns different videos together without explicitly comparing 3D shapes; and a 3D shape completion network that can extract the full shape of an object from partial observations. We also demonstrate the benefits of configuring networks to perform probabilistic predictions as well as of geometry-aware data augmentation schemes. We obtain state-of-the-art results on publicly-available benchmarks.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 8; 2022: 7; 2023: 4; 2024: 1; 2025: 3; 2026: 3.

26 papers.

Sort:

By area:

  1. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  2. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  3. 2023Visual Geometry Grounded Deep Structure From Motioncited by 227
  4. 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
  5. 2023RelPose++: Recovering 6D Poses from Sparse-view Observationscited by 87
  6. 2026PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulationcited by 82
  7. 2021Unsupervised Learning of 3D Object Categories from Videos in the Wildcited by 67
  8. 2021DOVE: Learning Deformable 3D Objects by Watching Videoscited by 61
  9. 2021NeuralDiff: Segmenting 3D objects that move in egocentric videoscited by 57
  10. 2021FiG-NeRF: Figure-Ground Neural Radiance Fields for 3D Object Category Modellingcited by 47
  11. 2024REACTO: Reconstructing Articulated Objects from a Single Videocited by 45
  12. 2025Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstructioncited by 44
14 more
  1. 2022Surface-Aligned Neural Radiance Fields for Controllable 3D Human Synthesiscited by 41
  2. 2021CoCoNets: Continuous Contrastive 3D Scene Representationscited by 19
  3. 2021Augmenting Implicit Neural Shape Representations with Explicit Deformation Fieldscited by 19
  4. 2022Depth Field Networks for Generalizable Multi-view Scene Representationcited by 17
  5. 2023MoDA: Modeling Deformable 3D Objects from Casual Videoscited by 13
  6. 2022Structural Causal 3D Reconstructioncited by 12
  7. 2025Unified Semantic Transformer for 3D Scene Understandingcited by 8
  8. 2021Lifting 2D Object Locations to 3D by Discounting LiDAR Outliers across Objects and Viewscited by 7
  9. 2026EventVGGT: Exploring Cross-Modal Distillation for Consistent Event-based Depth Estimationcited by 5
  10. 2022ViewNet: Unsupervised Viewpoint Estimation from Conditional Generationcited by 3
  11. 2022Accidental Turntables: Learning 3D Pose by Watching Objects Turncited by 1
  12. 2026Learning Geometric Representations from Videos for Spatial Intelligent Multimodal Large Language Modelscited by 1
  13. 2022Neural Camera Modelscited by 0
  14. 2023Unsupervised Style-based Explicit 3D Face Reconstruction from Single Imagecited by 0