mlsanityData to 7 Oct 2026

Structural Causal 3D Reconstruction

arXiv 2207.10156 ↗First posted 20 Jul 2022cs.LG cs.AI cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

This paper considers the problem of unsupervised 3D object reconstruction from in-the-wild single-view images. Due to ambiguity and intrinsic ill-posedness, this problem is inherently difficult to solve and therefore requires strong regularization to achieve disentanglement of different latent factors. Unlike existing works that introduce explicit regularizations into objective functions, we look into a different space for implicit regularization -- the structure of latent space. Specifically, we restrict the structure of latent space to capture a topological causal ordering of latent factors (i.e., representing causal dependency as a directed acyclic graph). We first show that different causal orderings matter for 3D reconstruction, and then explore several approaches to find a task-dependent causal factor ordering. Our experiments demonstrate that the latent space structure indeed serves as an implicit regularization and introduces an inductive bias beneficial for reconstruction.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 57 of its 88 references that are in the map. First posted on arXiv 20 Jul 2022.

Builds on

57 of 88 references.

References · 57

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  5. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  6. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  7. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  8. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  9. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  10. 2017End-to-end Recovery of Human Shape and Posecited by 883
  11. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  12. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 745
38 more
  1. 2018A Tutorial on Bayesian Optimizationcited by 734
  2. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 733
  3. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  4. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  5. 2017Neural 3D Mesh Renderercited by 437
  6. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  7. 2019DAG-GNN: DAG Structure Learning with Graph Neural Networkscited by 329
  8. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  9. 2019Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderercited by 221
  10. 2021D'ya like DAGs? A Survey on Structure Learning and Causal Discoverycited by 209
  11. 2021Towards Causal Representation Learningcited by 207
  12. 2017Learning a Multi-View Stereo Machinecited by 194
  13. 2019Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wildcited by 180
  14. 2017Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistencycited by 177
  15. 2016Learning a Predictable and Generative Vector Representation for Objectscited by 173
  16. 2019Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Imagescited by 164
  17. 2017MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstructioncited by 163
  18. 2017A Survey of Structure from Motioncited by 157
  19. 2020Monocular Expressive Body Regression through Body-Driven Attentioncited by 155
  20. 2017Learning Depth from Monocular Videos using Direct Methodscited by 154
  21. 2019GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstructioncited by 150
  22. 2017Morphable Face Models - An Open Frameworkcited by 138
  23. 2021Collaborative Regression of Expressive Bodies using Moderationcited by 137
  24. 2020Self-supervised Single-view 3D Reconstruction via Semantic Consistencycited by 127
  25. 2016Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervisioncited by 106
  26. 2019Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networkscited by 106
  27. 2019Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformationcited by 103
  28. 2015Learning to See by Movingcited by 101
  29. 2019Unsupervised 3D Pose Estimation with Geometric Self-Supervisioncited by 95
  30. 2018Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoningcited by 79
  31. 2020img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimationcited by 57
  32. 2019Learning single-image 3D reconstruction by generative modelling of shape, pose and shadingcited by 43
  33. 2018Exponential Convergence of the Deep Neural Network Approximation for Analytic Functionscited by 38
  34. 2018Learning View Priors for Single-view 3D Reconstructioncited by 35
  35. 2017Learning 3D Object Categories by Looking Around Themcited by 26
  36. 2017SilNet : Single- and Multi-View Reconstruction by Learning from Silhouettescited by 24
  37. 2018Generalization in anti-causal learningcited by 23
  38. 2021SphereFace Revived: Unifying Hyperspherical Face Recognitioncited by 23

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 7; 2024: 0; 2025: 2; 2026: 1.

12 papers.

  1. 2023MeshDiffusion: Score-based Generative 3D Mesh Modelingcited by 198
  2. 2023GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphscited by 96
  3. 2023Learning Disentangled Avatars with Hybrid 3D Representationscited by 44
  4. 2023Text-Guided Generation and Editing of Compositional 3D Avatarscited by 39
  5. 2023Ghost on the Shell: An Expressive Representation of General 3D Shapescited by 24
  6. 2025Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imagingcited by 20
  7. 2023Causal reasoning in typical computer vision taskscited by 12
  8. 2025CleanPose: Category-Level Object Pose Estimation via Causal Learning and Knowledge Distillationcited by 9
  9. 2022Vitruvio: 3D Building Meshes via Single Perspective Sketchescited by 5
  10. 2022Pearl Causal Hierarchy on Image Data: Intricacies & Challengescited by 3
  11. 2023Depth Insight -- Contribution of Different Features to Indoor Single-image Depth Estimationcited by 0
  12. 2026XYZFlow:Scaling Multi dimensional Shortcut Flows for Efficient Generative Modelingcited by 0