mlsanityData to 7 Oct 2026

Deep Convolutional Inverse Graphics Network

arXiv 1503.03167 ↗First posted 11 Mar 2015cs.CV cs.GR cs.LGcited by 121

Not on the map. Why?

Abstract (arXiv)

This paper presents the Deep Convolution Inverse Graphics Network (DC-IGN), a model that learns an interpretable representation of images. This representation is disentangled with respect to transformations such as out-of-plane rotations and lighting variations. The DC-IGN model is composed of multiple layers of convolution and de-convolution operators and is trained using the Stochastic Gradient Variational Bayes (SGVB) algorithm. We propose a training procedure to encourage neurons in the graphics code layer to represent a specific transformation (e.g. pose or light). Given a single input image, our model can generate new images of the same object with variations in pose and lighting. We present qualitative and quantitative results of the model's efficacy at learning a 3D rendering engine.

Key facts. Cited by 121 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Mar 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 37; 2022: 37; 2023: 21; 2024: 11; 2025: 13; 2026: 2.

121 papers.

Sort:

By area:

  1. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  2. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 364
  3. 2022CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learningcited by 342
  4. 2021GRAM: Generative Radiance Manifolds for 3D-Aware Image Generationcited by 216
  5. 2021Neural Articulated Radiance Fieldcited by 196
  6. 2023StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Modelscited by 154
  7. 2021Illiterate DALL-E Learns to Composecited by 147
  8. 2021A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representationcited by 113
  9. 2022Disentangled Representation Learningcited by 111
  10. 2021Geometry-Free View Synthesis: Transformers and no 3D Priorscited by 99
  11. 2022GlanceNets: Interpretabile, Leak-proof Concept-based Modelscited by 73
  12. 2024Advances in 3D Generation: A Surveycited by 62
38 more
  1. 2021CDFI: Compression-Driven Network Design for Frame Interpolationcited by 55
  2. 2022On the Principles of Parsimony and Self-Consistency for the Emergence of Intelligencecited by 50
  3. 2022Recent Advances for Quantum Neural Networks in Generative Learningcited by 39
  4. 2021DISSECT: Disentangled Simultaneous Explanations via Concept Traversalscited by 37
  5. 2023Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometrycited by 35
  6. 2021Video Autoencoder: self-supervised disentanglement of static 3D structure and motioncited by 34
  7. 2022Reversible Column Networkscited by 32
  8. 2023Leveraging sparse and shared feature activations for disentangled representation learningcited by 32
  9. 2022De-rendering 3D Objects in the Wildcited by 31
  10. 2021De-rendering the World's Revolutionary Artefactscited by 28
  11. 2021Where and What? Examining Interpretable Disentangled Representationscited by 27
  12. 2021Commutative Lie Group VAE for Disentanglement Learningcited by 27
  13. 2022Symmetry-Based Representations for Artificial and Biological General Intelligencecited by 26
  14. 2023GINA-3D: Learning to Generate Implicit Neural Assets in the Wildcited by 25
  15. 2021Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developmentscited by 23
  16. 2022DCI-ES: An Extended Disentanglement Framework with Connections to Identifiabilitycited by 23
  17. 2023Multifactor Sequential Disentanglement via Structured Koopman Autoencoderscited by 23
  18. 2022MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularizationcited by 22
  19. 2021Representing 3D Shapes with Probabilistic Directed Distance Fieldscited by 21
  20. 2021Learning disentangled representations via product manifold projectioncited by 20
  21. 2021Outdoor inverse rendering from a single image using multiview self-supervisioncited by 18
  22. 2022Homomorphism Autoencoder -- Learning Group Structured Representations from Observed Transitionscited by 18
  23. 2024TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Modelscited by 18
  24. 2022SPARF: Large-Scale Learning of 3D Sparse Radiance Fields from Few Input Imagescited by 17
  25. 2023Grounded Object Centric Learningcited by 17
  26. 2021Cloud2Curve: Generation and Vectorization of Parametric Sketchescited by 16
  27. 2023Self-Supervised Disentanglement by Leveraging Structure in Data Augmentationscited by 16
  28. 2021Disentangling Representations of Text by Masking Transformerscited by 15
  29. 20213D Shape Variational Autoencoder Latent Disentanglement via Mini-Batch Feature Swapping for Bodies and Facescited by 15
  30. 2023SAOR: Single-View Articulated Object Reconstructioncited by 15
  31. 2025Generative Models in Decision Making: A Surveycited by 14
  32. 2022NashAE: Disentangling Representations through Adversarial Covariance Minimizationcited by 13
  33. 2021The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agentscited by 12
  34. 2022An Empirical Study on Disentanglement of Negative-free Contrastive Learningcited by 12
  35. 2022Learning Conditional Variational Autoencoders with Missing Covariatescited by 10
  36. 2022Learning with Capsules: A Surveycited by 10
  37. 2023Sample and Predict Your Latent: Modality-free Sequential Disentanglement via Contrastive Estimationcited by 10
  38. 2023TUVF: Learning Generalizable Texture UV Radiance Fieldscited by 9

50 most cited of 121 All 121 (JSON)